Computer Vision and Pattern Recognition (cs.CV)

Abstract: The development of learning-based methods has greatly improved the detection of synapses from electron microscopy (EM) images. However, training a model for each dataset is time-consuming and requires extensive annotations. Additionally, it is difficult to apply a learned model to data from different brain regions due to variations in data distributions. In this paper, we present AdaSyn, a two-stage segmentation-based framework for domain adaptive synapse detection with weak point annotations. In the first stage, we address the detection problem by utilizing a segmentation-based pipeline to obtain synaptic instance masks. In the second stage, we improve model generalizability on target data by regenerating square masks to get high-quality pseudo labels. Benefiting from our high-accuracy detection results, we introduce the distance nearest principle to match paired pre-synapses and post-synapses. In the WASPSYN challenge at ISBI 2023, our method ranks the 1st place.

Abstract: Large language models exhibit enhanced zero-shot performance on various tasks when fine-tuned with instruction-following data. Multimodal instruction-following models extend these capabilities by integrating both text and images. However, existing models such as MiniGPT-4 face challenges in maintaining dialogue coherence in scenarios involving multiple images. A primary reason is the lack of a specialized dataset for this critical application. To bridge these gaps, we present SparklesChat, a multimodal instruction-following model for open-ended dialogues across multiple images. To support the training, we introduce SparklesDialogue, the first machine-generated dialogue dataset tailored for word-level interleaved multi-image and text interactions. Furthermore, we construct SparklesEval, a GPT-assisted benchmark for quantitatively assessing a model's conversational competence across multiple images and dialogue turns. Our experiments validate the effectiveness of SparklesChat in understanding and reasoning across multiple images and dialogue turns. Specifically, SparklesChat outperformed MiniGPT-4 on established vision-and-language benchmarks, including the BISON binary image selection task and the NLVR2 visual reasoning task. Moreover, SparklesChat scored 8.56 out of 10 on SparklesEval, substantially exceeding MiniGPT-4's score of 3.91 and nearing GPT-4's score of 9.26. Qualitative evaluations further demonstrate SparklesChat's generality in handling real-world applications. All resources will be available at https://github.com/HYPJUDY/Sparkles.

Abstract: While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical images in its training dataset. Nonetheless, gathering comprehensive datasets and training models that are universally applicable is particularly challenging due to the long-tail problem common in medical images. To address this gap, here we present a Self-Sampling Meta SAM (SSM-SAM) framework for few-shot medical image segmentation. Our innovation lies in the design of three key modules: 1) An online fast gradient descent optimizer, further optimized by a meta-learner, which ensures swift and robust adaptation to new tasks. 2) A Self-Sampling module designed to provide well-aligned visual prompts for improved attention allocation; and 3) A robust attention-based decoder specifically designed for medical few-shot learning to capture relationship between different slices. Extensive experiments on a popular abdominal CT dataset and an MRI dataset demonstrate that the proposed method achieves significant improvements over state-of-the-art methods in few-shot segmentation, with an average improvements of 10.21% and 1.80% in terms of DSC, respectively. In conclusion, we present a novel approach for rapid online adaptation in interactive image segmentation, adapting to a new organ in just 0.83 minutes. Code is publicly available on GitHub upon acceptance.

Abstract: Vectorized high-definition map online construction has garnered considerable attention in the field of autonomous driving research. Most existing approaches model changeable map elements using a fixed number of points, or predict local maps in a two-stage autoregressive manner, which may miss essential details and lead to error accumulation. Towards precise map element learning, we propose a simple yet effective architecture named PivotNet, which adopts unified pivot-based map representations and is formulated as a direct set prediction paradigm. Concretely, we first propose a novel Point-to-Line Mask module to encode both the subordinate and geometrical point-line priors in the network. Then, a well-designed Pivot Dynamic Matching module is proposed to model the topology in dynamic point sequences by introducing the concept of sequence matching. Furthermore, to supervise the position and topology of the vectorized point predictions, we propose a Dynamic Vectorized Sequence loss. Extensive experiments and ablations show that PivotNet is remarkably superior to other SOTAs by 5.9 mAP at least. The code will be available soon.

Abstract: We present Point-TTA, a novel test-time adaptation framework for point cloud registration (PCR) that improves the generalization and the performance of registration models. While learning-based approaches have achieved impressive progress, generalization to unknown testing environments remains a major challenge due to the variations in 3D scans. Existing methods typically train a generic model and the same trained model is applied on each instance during testing. This could be sub-optimal since it is difficult for the same model to handle all the variations during testing. In this paper, we propose a test-time adaptation approach for PCR. Our model can adapt to unseen distributions at test-time without requiring any prior knowledge of the test data. Concretely, we design three self-supervised auxiliary tasks that are optimized jointly with the primary PCR task. Given a test instance, we adapt our model using these auxiliary tasks and the updated model is used to perform the inference. During training, our model is trained using a meta-auxiliary learning approach, such that the adapted model via auxiliary tasks improves the accuracy of the primary task. Experimental results demonstrate the effectiveness of our approach in improving generalization of point cloud registration and outperforming other state-of-the-art approaches.

Abstract: Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard benchmarks, they tend to experience significant performance drops when the test data have different distributions from the training data. To address this issue, this paper proposes a test-time adaption approach to enhance model generality of point cloud upsampling. The proposed approach leverages meta-learning to explicitly learn network parameters for test-time adaption. Our method does not require any prior information about the test data. During meta-training, the model parameters are learned from a collection of instance-level tasks, each of which consists of a sparse-dense pair of point clouds from the training data. During meta-testing, the trained model is fine-tuned with a few gradient updates to produce a unique set of network parameters for each test instance. The updated model is then used for the final prediction. Our framework is generic and can be applied in a plug-and-play manner with existing backbone networks in point cloud upsampling. Extensive experiments demonstrate that our approach improves the performance of state-of-the-art models.

Abstract: Nighttime person Re-ID (person re-identification in the nighttime) is a very important and challenging task for visual surveillance but it has not been thoroughly investigated. Under the low illumination condition, the performance of person Re-ID methods usually sharply deteriorates. To address the low illumination challenge in nighttime person Re-ID, this paper proposes an Illumination Distillation Framework (IDF), which utilizes illumination enhancement and illumination distillation schemes to promote the learning of Re-ID models. Specifically, IDF consists of a master branch, an illumination enhancement branch, and an illumination distillation module. The master branch is used to extract the features from a nighttime image. The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features. However, nighttime and enhanced features usually contain data noise due to unstable lighting conditions and enhancement failures. To fully exploit the complementary benefits of nighttime and enhanced features while suppressing data noise, we propose an illumination distillation module. In particular, the illumination distillation module fuses the features from two branches through a bottleneck fusion model and then uses the fused features to guide the learning of both branches in a distillation manner. In addition, we build a real-world nighttime person Re-ID dataset, named Night600, which contains 600 identities captured from different viewpoints and nighttime illumination conditions under complex outdoor environments. Experimental results demonstrate that our IDF can achieve state-of-the-art performance on two nighttime person Re-ID datasets (i.e., Night600 and Knight ). We will release our code and dataset at https://github.com/Alexadlu/IDF.

Abstract: Latent diffusers revolutionized the generative AI and inspired creative art. When denoising the latent, the predicted original image at each step collectively animates the formation. However, the animation is limited by the denoising nature of the diffuser, and only renders a sharpening process. This work presents Latent Painter, which uses the latent as the canvas, and the diffuser predictions as the plan, to generate painting animation. Latent Painter also transits one generated image to another, which can happen between images from two different sets of checkpoints.

Abstract: Recent advancements in real image editing have been attributed to the exploration of Generative Adversarial Networks (GANs) latent space. However, the main challenge of this procedure is GAN inversion, which aims to map the image to the latent space accurately. Existing methods that work on extended latent space $W+$ are unable to achieve low distortion and high editability simultaneously. To address this issue, we propose an approach which works in native latent space $W$ and tunes the generator network to restore missing image details. We introduce a novel regularization strategy with learnable coefficients obtained by training randomized StyleGAN 2 model - WRanGAN. This method outperforms traditional approaches in terms of reconstruction quality and computational efficiency, achieving the lowest distortion with 4 times fewer parameters. Furthermore, we observe a slight improvement in the quality of constructing hyperplanes corresponding to binary image attributes. We demonstrate the effectiveness of our approach on two complex datasets: Flickr-Faces-HQ and LSUN Church.

Abstract: We propose MVDream, a multi-view diffusion model that is able to generate geometrically consistent multi-view images from a given text prompt. By leveraging image diffusion models pre-trained on large-scale web datasets and a multi-view dataset rendered from 3D assets, the resulting multi-view diffusion model can achieve both the generalizability of 2D diffusion and the consistency of 3D data. Such a model can thus be applied as a multi-view prior for 3D generation via Score Distillation Sampling, where it greatly improves the stability of existing 2D-lifting methods by solving the 3D consistency problem. Finally, we show that the multi-view diffusion model can also be fine-tuned under a few shot setting for personalized 3D generation, i.e. DreamBooth3D application, where the consistency can be maintained after learning the subject identity.

Abstract: Lidar point clouds, as a type of data with accurate distance perception, can effectively represent the motion and posture of objects in three-dimensional space. However, the sparsity and disorderliness of point clouds make it challenging to extract features directly from them. Many studies have addressed this issue by transforming point clouds into regular voxel representations. However, these methods often lead to the loss of fine-grained local feature information due to downsampling. Moreover, the sparsity of point clouds poses difficulties in efficiently aggregating features in 3D feature layers using voxel-based two-stage methods. To address these issues, this paper proposes a two-stage 3D detection framework called MS$^{2}$3D. In MS$^{2}$3D, we utilize small-sized voxels to extract fine-grained local features and large-sized voxels to capture long-range local features. Additionally, we propose a method for constructing 3D feature layers using multi-scale semantic feature points, enabling the transformation of sparse 3D feature layers into more compact representations. Furthermore, we compute the offset between feature points in the 3D feature layers and the centroid of objects, aiming to bring them as close as possible to the object's center. It significantly enhances the efficiency of feature aggregation. To validate the effectiveness of our method, we evaluated our method on the KITTI dataset and ONCE dataset together.

Abstract: Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects. While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods. The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions. Experimental results show that our method 1) significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes on the MS COCO dataset, and 2) achieves better generalization ability on the LVIS and Objects365 datasets.

Abstract: To enable meaningful robotic manipulation of objects in the real-world, 6D pose estimation is one of the critical aspects. Most existing approaches have difficulties to extend predictions to scenarios where novel object instances are continuously introduced, especially with heavy occlusions. In this work, we propose a few-shot pose estimation (FSPE) approach called SA6D, which uses a self-adaptive segmentation module to identify the novel target object and construct a point cloud model of the target object using only a small number of cluttered reference images. Unlike existing methods, SA6D does not require object-centric reference images or any additional object information, making it a more generalizable and scalable solution across categories. We evaluate SA6D on real-world tabletop object datasets and demonstrate that SA6D outperforms existing FSPE methods, particularly in cluttered scenes with occlusions, while requiring fewer reference images.

Abstract: The unstructured nature of point clouds demands that local aggregation be adaptive to different local structures. Previous methods meet this by explicitly embedding spatial relations into each aggregation process. Although this coupled approach has been shown effective in generating clear semantics, aggregation can be greatly slowed down due to repeated relation learning and redundant computation to mix directional and point features. In this work, we propose to decouple the explicit modelling of spatial relations from local aggregation. We theoretically prove that basic neighbor pooling operations can too function without loss of clarity in feature fusion, so long as essential spatial information has been encoded in point features. As an instantiation of decoupled local aggregation, we present DeLA, a lightweight point network, where in each learning stage relative spatial encodings are first formed, and only pointwise convolutions plus edge max-pooling are used for local aggregation then. Further, a regularization term is employed to reduce potential ambiguity through the prediction of relative coordinates. Conceptually simple though, experimental results on five classic benchmarks demonstrate that DeLA achieves state-of-the-art performance with reduced or comparable latency. Specifically, DeLA achieves over 90\% overall accuracy on ScanObjectNN and 74\% mIoU on S3DIS Area 5. Our code is available at https://github.com/Matrix-ASC/DeLA .

Abstract: The vast majority of people who suffer unexpected cardiac arrest are performed cardiopulmonary resuscitation (CPR) by passersby in a desperate attempt to restore life, but endeavors turn out to be fruitless on account of disqualification. Fortunately, many pieces of research manifest that disciplined training will help to elevate the success rate of resuscitation, which constantly desires a seamless combination of novel techniques to yield further advancement. To this end, we collect a custom CPR video dataset in which trainees make efforts to behave resuscitation on mannequins independently in adherence to approved guidelines, thereby devising an auxiliary toolbox to assist supervision and rectification of intermediate potential issues via modern deep learning methodologies. Our research empirically views this problem as a temporal action segmentation (TAS) task in computer vision, which aims to segment an untrimmed video at a frame-wise level. Here, we propose a Prompt-enhanced hierarchical Transformer (PhiTrans) that integrates three indispensable modules, including a textual prompt-based Video Features Extractor (VFE), a transformer-based Action Segmentation Executor (ASE), and a regression-based Prediction Refinement Calibrator (PRC). The backbone of the model preferentially derives from applications in three approved public datasets (GTEA, 50Salads, and Breakfast) collected for TAS tasks, which accounts for the excavation of the segmentation pipeline on the CPR dataset. In general, we unprecedentedly probe into a feasible pipeline that genuinely elevates the CPR instruction qualification via action segmentation in conjunction with cutting-edge deep learning techniques. Associated experiments advocate our implementation with multiple metrics surpassing 91.0%.

Abstract: Accurate and robust correspondence matching is of utmost importance for various 3D computer vision tasks. However, traditional explicit programming-based methods often struggle to handle challenging scenarios, and deep learning-based methods require large well-labeled datasets for network training. In this article, we introduce Epipolar-Constrained Cascade Correspondence (E3CM), a novel approach that addresses these limitations. Unlike traditional methods, E3CM leverages pre-trained convolutional neural networks to match correspondence, without requiring annotated data for any network training or fine-tuning. Our method utilizes epipolar constraints to guide the matching process and incorporates a cascade structure for progressive refinement of matches. We extensively evaluate the performance of E3CM through comprehensive experiments and demonstrate its superiority over existing methods. To promote further research and facilitate reproducibility, we make our source code publicly available at https://mias.group/E3CM.

Abstract: The principle underlying most existing continual learning (CL) methods is to prioritize stability by penalizing changes in parameters crucial to old tasks, while allowing for plasticity in other parameters. The importance of weights for each task can be determined either explicitly through learning a task-specific mask during training (e.g., parameter isolation-based approaches) or implicitly by introducing a regularization term (e.g., regularization-based approaches). However, all these methods assume that the importance of weights for each task is unknown prior to data exposure. In this paper, we propose ScrollNet as a scrolling neural network for continual learning. ScrollNet can be seen as a dynamic network that assigns the ranking of weight importance for each task before data exposure, thus achieving a more favorable stability-plasticity tradeoff during sequential task learning by reassigning this ranking for different tasks. Additionally, we demonstrate that ScrollNet can be combined with various CL methods, including regularization-based and replay-based approaches. Experimental results on CIFAR100 and TinyImagenet datasets show the effectiveness of our proposed method. We release our code at https://github.com/FireFYF/ScrollNet.git.

Abstract: In the rapidly evolving digital era, the analysis of document layouts plays a pivotal role in automated information extraction and interpretation. In our work, we have trained MViTv2 transformer model architecture with cascaded mask R-CNN on BaDLAD dataset to extract text box, paragraphs, images and tables from a document. After training on 20365 document images for 36 epochs in a 3 phase cycle, we achieved a training loss of 0.2125 and a mask loss of 0.19. Our work extends beyond training, delving into the exploration of potential enhancement avenues. We investigate the impact of rotation and flip augmentation, the effectiveness of slicing input images pre-inference, the implications of varying the resolution of the transformer backbone, and the potential of employing a dual-pass inference to uncover missed text-boxes. Through these explorations, we observe a spectrum of outcomes, where some modifications result in tangible performance improvements, while others offer unique insights for future endeavors.

Abstract: Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. Typically, this approach involves randomly masking patches (tokens) in input images, with the masking strategy remaining unchanged during training. In this paper, we propose a curriculum learning approach that updates the masking strategy to continually increase the complexity of the self-supervised reconstruction task. We conjecture that, by gradually increasing the task complexity, the model can learn more sophisticated and transferable representations. To facilitate this, we introduce a novel learnable masking module that possesses the capability to generate masks of different complexities, and integrate the proposed module into masked autoencoders (MAE). Our module is jointly trained with the MAE, while adjusting its behavior during training, transitioning from a partner to the MAE (optimizing the same reconstruction loss) to an adversary (optimizing the opposite loss), while passing through a neutral state. The transition between these behaviors is smooth, being regulated by a factor that is multiplied with the reconstruction loss of the masking module. The resulting training procedure generates an easy-to-hard curriculum. We train our Curriculum-Learned Masked Autoencoder (CL-MAE) on ImageNet and show that it exhibits superior representation learning capabilities compared to MAE. The empirical results on five downstream tasks confirm our conjecture, demonstrating that curriculum learning can be successfully used to self-supervise masked autoencoders.

Abstract: In this paper, we tackle the challenging task of learning a generalizable human NeRF model from a monocular video. Although existing generalizable human NeRFs have achieved impressive results, they require muti-view images or videos which might not be always available. On the other hand, some works on free-viewpoint rendering of human from monocular videos cannot be generalized to unseen identities. In view of these limitations, we propose GHuNeRF to learn a generalizable human NeRF model from a monocular video of the human performer. We first introduce a visibility-aware aggregation scheme to compute vertex-wise features, which is used to construct a 3D feature volume. The feature volume can only represent the overall geometry of the human performer with insufficient accuracy due to the limited resolution. To solve this, we further enhance the volume feature with temporally aligned point-wise features using an attention mechanism. Finally, the enhanced feature is used for predicting density and color for each sampled point. A surface-guided sampling strategy is also introduced to improve the efficiency for both training and inference. We validate our approach on the widely-used ZJU-MoCap dataset, where we achieve comparable performance with existing multi-view video based approaches. We also test on the monocular People-Snapshot dataset and achieve better performance than existing works when only monocular video is used.

Abstract: Stable diffusion, a generative model used in text-to-image synthesis, frequently encounters resolution-induced composition problems when generating images of varying sizes. This issue primarily stems from the model being trained on pairs of single-scale images and their corresponding text descriptions. Moreover, direct training on images of unlimited sizes is unfeasible, as it would require an immense number of text-image pairs and entail substantial computational expenses. To overcome these challenges, we propose a two-stage pipeline named Any-Size-Diffusion (ASD), designed to efficiently generate well-composed images of any size, while minimizing the need for high-memory GPU resources. Specifically, the initial stage, dubbed Any Ratio Adaptability Diffusion (ARAD), leverages a selected set of images with a restricted range of ratios to optimize the text-conditional diffusion model, thereby improving its ability to adjust composition to accommodate diverse image sizes. To support the creation of images at any desired size, we further introduce a technique called Fast Seamless Tiled Diffusion (FSTD) at the subsequent stage. This method allows for the rapid enlargement of the ASD output to any high-resolution size, avoiding seaming artifacts or memory overloads. Experimental results on the LAION-COCO and MM-CelebA-HQ benchmarks demonstrate that ASD can produce well-structured images of arbitrary sizes, cutting down the inference time by 2x compared to the traditional tiled algorithm.

Abstract: The growth of misinformation and re-contextualized media in social media and news leads to an increasing need for fact-checking methods. Concurrently, the advancement in generative models makes cheapfakes and deepfakes both easier to make and harder to detect. In this paper, we present a novel approach using generative image models to our advantage for detecting Out-of-Context (OOC) use of images-caption pairs in news. We present two new datasets with a total of $6800$ images generated using two different generative models including (1) DALL-E 2, and (2) Stable-Diffusion. We are confident that the method proposed in this paper can further research on generative models in the field of cheapfake detection, and that the resulting datasets can be used to train and evaluate new models aimed at detecting cheapfakes. We run a preliminary qualitative and quantitative analysis to evaluate the performance of each image generation model for this task, and evaluate a handful of methods for computing image similarity.

Abstract: Owing to its significant success, the prior imposed on gradient maps has consistently been a subject of great interest in the field of image processing. Total variation (TV), one of the most representative regularizers, is known for its ability to capture the sparsity of gradient maps. Nonetheless, TV and its variants often underestimate the gradient maps, leading to the weakening of edges and details whose gradients should not be zero in the original image. Recently, total deep variation (TDV) has been introduced, assuming the sparsity of feature maps, which provides a flexible regularization learned from large-scale datasets for a specific task. However, TDV requires retraining when the image or task changes, limiting its versatility. In this paper, we propose a neural gradient regularizer (NGR) that expresses the gradient map as the output of a neural network. Unlike existing methods, NGR does not rely on the sparsity assumption, thereby avoiding the underestimation of gradient maps. NGR is applicable to various image types and different image processing tasks, functioning in a zero-shot learning fashion, making it a versatile and plug-and-play regularizer. Extensive experimental results demonstrate the superior performance of NGR over state-of-the-art counterparts for a range of different tasks, further validating its effectiveness and versatility.

Abstract: In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions. However, this conventional paradigm encounters significant challenges, most notably in terms of the generation of lackluster initial proposals and a pronounced deceleration in inference speed. Recognizing these limitations, we introduce an innovative end-to-end Superpoint-Text Matching Network (3D-STMN) that is enriched by dependency-driven insights. One of the keystones of our model is the Superpoint-Text Matching (STM) mechanism. Unlike traditional methods that navigate through instance proposals, STM directly correlates linguistic indications with their respective superpoints, clusters of semantically related points. This architectural decision empowers our model to efficiently harness cross-modal semantic relationships, primarily leveraging densely annotated superpoint-text pairs, as opposed to the more sparse instance-text pairs. In pursuit of enhancing the role of text in guiding the segmentation process, we further incorporate the Dependency-Driven Interaction (DDI) module to deepen the network's semantic comprehension of referring expressions. Using the dependency trees as a beacon, this module discerns the intricate relationships between primary terms and their associated descriptors in expressions, thereby elevating both the localization and segmentation capacities of our model. Comprehensive experiments on the ScanRefer benchmark reveal that our model not only set new performance standards, registering an mIoU gain of 11.7 points but also achieve a staggering enhancement in inference speed, surpassing traditional methods by 95.7 times. The code and models are available at https://github.com/sosppxo/3D-STMN.

Abstract: Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training data. The insufficiency of labeled training SAR images limits the recognition performance and even invalidates some ATR methods. Furthermore, under few labeled training data, many existing CNNs are even ineffective. To address these challenges, we propose a Semi-supervised SAR ATR Framework with transductive Auxiliary Segmentation (SFAS). The proposed framework focuses on exploiting the transductive generalization on available unlabeled samples with an auxiliary loss serving as a regularizer. Through auxiliary segmentation of unlabeled SAR samples and information residue loss (IRL) in training, the framework can employ the proposed training loop process and gradually exploit the information compilation of recognition and segmentation to construct a helpful inductive bias and achieve high performance. Experiments conducted on the MSTAR dataset have shown the effectiveness of our proposed SFAS for few-shot learning. The recognition performance of 94.18\% can be achieved under 20 training samples in each class with simultaneous accurate segmentation results. Facing variances of EOCs, the recognition ratios are higher than 88.00\% when 10 training samples each class.

Abstract: Face-to-face communication is a common scenario including roles of speakers and listeners. Most existing research methods focus on producing speaker videos, while the generation of listener heads remains largely overlooked. Responsive listening head generation is an important task that aims to model face-to-face communication scenarios by generating a listener head video given a speaker video and a listener head image. An ideal generated responsive listening video should respond to the speaker with attitude or viewpoint expressing while maintaining diversity in interaction patterns and accuracy in listener identity information. To achieve this goal, we propose the \textbf{M}ulti-\textbf{F}aceted \textbf{R}esponsive Listening Head Generation Network (MFR-Net). Specifically, MFR-Net employs the probabilistic denoising diffusion model to predict diverse head pose and expression features. In order to perform multi-faceted response to the speaker video, while maintaining accurate listener identity preservation, we design the Feature Aggregation Module to boost listener identity features and fuse them with other speaker-related features. Finally, a renderer finetuned with identity consistency loss produces the final listening head videos. Our extensive experiments demonstrate that MFR-Net not only achieves multi-faceted responses in diversity and speaker identity information but also in attitude and viewpoint expression.

Abstract: Uncovering novel drug candidates for treating complex diseases remain one of the most challenging tasks in early discovery research. To tackle this challenge, biopharma research established a standardized high content imaging protocol that tags different cellular compartments per image channel. In order to judge the experimental outcome, the scientist requires knowledge about the channel importance with respect to a certain phenotype for decoding the underlying biology. In contrast to traditional image analysis approaches, such experiments are nowadays preferably analyzed by deep learning based approaches which, however, lack crucial information about the channel importance. To overcome this limitation, we present a novel approach which utilizes multi-spectral information of high content images to interpret a certain aspect of cellular biology. To this end, we base our method on image blending concepts with alpha compositing for an arbitrary number of channels. More specifically, we introduce DCMIX, a lightweight, scaleable and end-to-end trainable mixing layer which enables interpretable predictions in high content imaging while retaining the benefits of deep learning based methods. We employ an extensive set of experiments on both MNIST and RXRX1 datasets, demonstrating that DCMIX learns the biologically relevant channel importance without scarifying prediction performance.

Abstract: Despite recent advancements in image generation, diffusion models still remain largely underexplored in Earth Observation. In this paper we show that state-of-the-art pretrained diffusion models can be conditioned on cartographic data to generate realistic satellite images. We provide two large datasets of paired OpenStreetMap images and satellite views over the region of Mainland Scotland and the Central Belt. We train a ControlNet model and qualitatively evaluate the results, demonstrating that both image quality and map fidelity are possible. Finally, we provide some insights on the opportunities and challenges of applying these models for remote sensing. Our model weights and code for creating the dataset are publicly available at https://github.com/miquel-espinosa/map-sat.

Abstract: We consider the problem of composed image retrieval that takes an input query consisting of an image and a modification text indicating the desired changes to be made on the image and retrieves images that match these changes. Current state-of-the-art techniques that address this problem use global features for the retrieval, resulting in incorrect localization of the regions of interest to be modified because of the global nature of the features, more so in cases of real-world, in-the-wild images. Since modifier texts usually correspond to specific local changes in an image, it is critical that models learn local features to be able to both localize and retrieve better. To this end, our key novelty is a new gradient-attention-based learning objective that explicitly forces the model to focus on the local regions of interest being modified in each retrieval step. We achieve this by first proposing a new visual image attention computation technique, which we call multi-modal gradient attention (MMGrad) that is explicitly conditioned on the modifier text. We next demonstrate how MMGrad can be incorporated into an end-to-end model training strategy with a new learning objective that explicitly forces these MMGrad attention maps to highlight the correct local regions corresponding to the modifier text. By training retrieval models with this new loss function, we show improved grounding by means of better visual attention maps, leading to better explainability of the models as well as competitive quantitative retrieval performance on standard benchmark datasets.

Abstract: The SoccerNet 2023 tracking challenge requires the detection and tracking of soccer players and the ball. In this work, we present our approach to tackle these tasks separately. We employ a state-of-the-art online multi-object tracker and a contemporary object detector for player tracking. To overcome the limitations of our online approach, we incorporate a post-processing stage using interpolation and appearance-free track merging. Additionally, an appearance-based track merging technique is used to handle the termination and creation of tracks far from the image boundaries. Ball tracking is formulated as single object detection, and a fine-tuned YOLOv8l detector with proprietary filtering improves the detection precision. Our method achieves 3rd place on the SoccerNet 2023 tracking challenge with a HOTA score of 66.27.

Abstract: Motion capture from a limited number of inertial measurement units (IMUs) has important applications in health, human performance, and virtual reality. Real-world limitations and application-specific goals dictate different IMU configurations (i.e., number of IMUs and chosen attachment body segments), trading off accuracy and practicality. Although recent works were successful in accurately reconstructing whole-body motion from six IMUs, these systems only work with a specific IMU configuration. Here we propose a single diffusion generative model, Diffusion Inertial Poser (DiffIP), which reconstructs human motion in real-time from arbitrary IMU configurations. We show that DiffIP has the benefit of flexibility with respect to the IMU configuration while being as accurate as the state-of-the-art for the commonly used six IMU configuration. Our system enables selecting an optimal configuration for different applications without retraining the model. For example, when only four IMUs are available, DiffIP found that the configuration that minimizes errors in joint kinematics instruments the thighs and forearms. However, global translation reconstruction is better when instrumenting the feet instead of the thighs. Although our approach is agnostic to the underlying model, we built DiffIP based on physiologically realistic musculoskeletal models to enable use in biomedical research and health applications.

Abstract: Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of vision-language tasks. Prior arts usually focus on how to align visual and textual features, but strategies for improving the robustness of model and speeding up model convergence are left insufficiently explored. In this paper, we propose a novel method ViLTA, comprising of two components to further facilitate the model to learn fine-grained representations among image-text pairs. For Masked Language Modeling (MLM), we propose a cross-distillation method to generate soft labels to enhance the robustness of model, which alleviates the problem of treating synonyms of masked words as negative samples in one-hot labels. For Image-Text Matching (ITM), we leverage the current language encoder to synthesize hard negatives based on the context of language input, encouraging the model to learn high-quality representations by increasing the difficulty of the ITM task. By leveraging the above techniques, our ViLTA can achieve better performance on various vision-language tasks. Extensive experiments on benchmark datasets demonstrate that the effectiveness of ViLTA and its promising potential for vision-language pre-training.

Abstract: Vehicle-to-everything (V2X) autonomous driving opens up a promising direction for developing a new generation of intelligent transportation systems. Collaborative perception (CP) as an essential component to achieve V2X can overcome the inherent limitations of individual perception, including occlusion and long-range perception. In this survey, we provide a comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community. Specifically, we first introduce the architecture and workflow of typical V2X systems, which affords a broader perspective to understand the entire V2X system and the role of CP within it. Then, we thoroughly summarize and analyze existing V2X perception datasets and CP methods. Particularly, we introduce numerous CP methods from various crucial perspectives, including collaboration stages, roadside sensors placement, latency compensation, performance-bandwidth trade-off, attack/defense, pose alignment, etc. Moreover, we conduct extensive experimental analyses to compare and examine current CP methods, revealing some essential and unexplored insights. Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue. Also, we examine methods under different LiDAR ranges. To study the model robustness, we further investigate the effects of various simulated real-world noises on the performance of different CP methods, covering communication latency, lossy communication, localization errors, and mixed noises. In addition, we look into the sim-to-real generalization ability of existing CP methods. At last, we thoroughly discuss issues and challenges, highlighting promising directions for future efforts. Our codes for experimental analysis will be public at https://github.com/memberRE/Collaborative-Perception.

Abstract: Sketch-based terrain generation seeks to create realistic landscapes for virtual environments in various applications such as computer games, animation and virtual reality. Recently, deep learning based terrain generation has emerged, notably the ones based on generative adversarial networks (GAN). However, these methods often struggle to fulfill the requirements of flexible user control and maintain generative diversity for realistic terrain. Therefore, we propose a novel diffusion-based method, namely terrain diffusion network (TDN), which actively incorporates user guidance for enhanced controllability, taking into account terrain features like rivers, ridges, basins, and peaks. Instead of adhering to a conventional monolithic denoising process, which often compromises the fidelity of terrain details or the alignment with user control, a multi-level denoising scheme is proposed to generate more realistic terrains by taking into account fine-grained details, particularly those related to climatic patterns influenced by erosion and tectonic activities. Specifically, three terrain synthesisers are designed for structural, intermediate, and fine-grained level denoising purposes, which allow each synthesiser concentrate on a distinct terrain aspect. Moreover, to maximise the efficiency of our TDN, we further introduce terrain and sketch latent spaces for the synthesizers with pre-trained terrain autoencoders. Comprehensive experiments on a new dataset constructed from NASA Topology Images clearly demonstrate the effectiveness of our proposed method, achieving the state-of-the-art performance. Our code and dataset will be publicly available.

Abstract: Deployment of Deep Neural Networks in medical imaging is hindered by distribution shift between training data and data processed after deployment, causing performance degradation. Post-Deployment Adaptation (PDA) addresses this by tailoring a pre-trained, deployed model to the target data distribution using limited labelled or entirely unlabelled target data, while assuming no access to source training data as they cannot be deployed with the model due to privacy concerns and their large size. This makes reliable adaptation challenging due to limited learning signal. This paper challenges this assumption and introduces FedPDA, a novel adaptation framework that brings the utility of learning from remote data from Federated Learning into PDA. FedPDA enables a deployed model to obtain information from source data via remote gradient exchange, while aiming to optimize the model specifically for the target domain. Tailored for FedPDA, we introduce a novel optimization method StarAlign (Source-Target Remote Gradient Alignment) that aligns gradients between source-target domain pairs by maximizing their inner product, to facilitate learning a target-specific model. We demonstrate the method's effectiveness using multi-center databases for the tasks of cancer metastases detection and skin lesion classification, where our method compares favourably to previous work. Code is available at: https://github.com/FelixWag/StarAlign

Abstract: Binary silhouettes and keypoint-based skeletons have dominated human gait recognition studies for decades since they are easy to extract from video frames. Despite their success in gait recognition for in-the-lab environments, they usually fail in real-world scenarios due to their low information entropy for gait representations. To achieve accurate gait recognition in the wild, this paper presents a novel gait representation, named Gait Parsing Sequence (GPS). GPSs are sequences of fine-grained human segmentation, i.e., human parsing, extracted from video frames, so they have much higher information entropy to encode the shapes and dynamics of fine-grained human parts during walking. Moreover, to effectively explore the capability of the GPS representation, we propose a novel human parsing-based gait recognition framework, named ParsingGait. ParsingGait contains a Convolutional Neural Network (CNN)-based backbone and two light-weighted heads. The first head extracts global semantic features from GPSs, while the other one learns mutual information of part-level features through Graph Convolutional Networks to model the detailed dynamics of human walking. Furthermore, due to the lack of suitable datasets, we build the first parsing-based dataset for gait recognition in the wild, named Gait3D-Parsing, by extending the large-scale and challenging Gait3D dataset. Based on Gait3D-Parsing, we comprehensively evaluate our method and existing gait recognition methods. The experimental results show a significant improvement in accuracy brought by the GPS representation and the superiority of ParsingGait. The code and dataset are available at https://gait3d.github.io/gait3d-parsing-hp .

Abstract: Generating 3D faces from textual descriptions has a multitude of applications, such as gaming, movie, and robotics. Recent progresses have demonstrated the success of unconditional 3D face generation and text-to-3D shape generation. However, due to the limited text-3D face data pairs, text-driven 3D face generation remains an open problem. In this paper, we propose a text-guided 3D faces generation method, refer as TG-3DFace, for generating realistic 3D faces using text guidance. Specifically, we adopt an unconditional 3D face generation framework and equip it with text conditions, which learns the text-guided 3D face generation with only text-2D face data. On top of that, we propose two text-to-face cross-modal alignment techniques, including the global contrastive learning and the fine-grained alignment module, to facilitate high semantic consistency between generated 3D faces and input texts. Besides, we present directional classifier guidance during the inference process, which encourages creativity for out-of-domain generations. Compared to the existing methods, TG-3DFace creates more realistic and aesthetically pleasing 3D faces, boosting 9% multi-view consistency (MVIC) over Latent3D. The rendered face images generated by TG-3DFace achieve higher FID and CLIP score than text-to-2D face/image generation models, demonstrating our superiority in generating realistic and semantic-consistent textures.

Abstract: Zero-shot referring image segmentation is a challenging task because it aims to find an instance segmentation mask based on the given referring descriptions, without training on this type of paired data. Current zero-shot methods mainly focus on using pre-trained discriminative models (e.g., CLIP). However, we have observed that generative models (e.g., Stable Diffusion) have potentially understood the relationships between various visual elements and text descriptions, which are rarely investigated in this task. In this work, we introduce a novel Referring Diffusional segmentor (Ref-Diff) for this task, which leverages the fine-grained multi-modal information from generative models. We demonstrate that without a proposal generator, a generative model alone can achieve comparable performance to existing SOTA weakly-supervised models. When we combine both generative and discriminative models, our Ref-Diff outperforms these competing methods by a significant margin. This indicates that generative models are also beneficial for this task and can complement discriminative models for better referring segmentation. Our code is publicly available at https://github.com/kodenii/Ref-Diff.

Abstract: A new method is proposed for human motion prediction by learning temporal and spatial dependencies. Recently, multiscale graphs have been developed to model the human body at higher abstraction levels, resulting in more stable motion prediction. Current methods however predetermine scale levels and combine spatially proximal joints to generate coarser scales based on human priors, even though movement patterns in different motion sequences vary and do not fully comply with a fixed graph of spatially connected joints. Another problem with graph convolutional methods is mode collapse, in which predicted poses converge around a mean pose with no discernible movements, particularly in long-term predictions. To tackle these issues, we propose ResChunk, an end-to-end network which explores dynamically correlated body components based on the pairwise relationships between all joints in individual sequences. ResChunk is trained to learn the residuals between target sequence chunks in an autoregressive manner to enforce the temporal connectivities between consecutive chunks. It is hence a sequence-to-sequence prediction network which considers dynamic spatio-temporal features of sequences at multiple levels. Our experiments on two challenging benchmark datasets, CMU Mocap and Human3.6M, demonstrate that our proposed method is able to effectively model the sequence information for motion prediction and outperform other techniques to set a new state-of-the-art. Our code is available at https://github.com/MohsenZand/ResChunk.

Abstract: Semantic image segmentation is a critical component in many computer vision systems, such as autonomous driving. In such applications, adverse conditions (heavy rain, night time, snow, extreme lighting) on the one hand pose specific challenges, yet are typically underrepresented in the available datasets. Generating more training data is cumbersome and expensive, and the process itself is error-prone due to the inherent aleatoric uncertainty. To address this challenging problem, we propose BTSeg, which exploits image-level correspondences as weak supervision signal to learn a segmentation model that is agnostic to adverse conditions. To this end, our approach uses the Barlow twins loss from the field of unsupervised learning and treats images taken at the same location but under different adverse conditions as "augmentations" of the same unknown underlying base image. This allows the training of a segmentation model that is robust to appearance changes introduced by different adverse conditions. We evaluate our approach on ACDC and the new challenging ACG benchmark to demonstrate its robustness and generalization capabilities. Our approach performs favorably when compared to the current state-of-the-art methods, while also being simpler to implement and train. The code will be released upon acceptance.

Abstract: Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by progressively modeling the amodal segmentation. C2F-Seg initially reduces the learning space from the pixel-level image space to the vector-quantized latent space. This enables us to better handle long-range dependencies and learn a coarse-grained amodal segment from visual features and visible segments. However, this latent space lacks detailed information about the object, which makes it difficult to provide a precise segmentation directly. To address this issue, we propose a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation. To help the studies of amodal object segmentation, we create a synthetic amodal dataset, named as MOViD-Amodal (MOViD-A), which can be used for both image and video amodal object segmentation. We extensively evaluate our model on two benchmark datasets: KINS and COCO-A. Our empirical results demonstrate the superiority of C2F-Seg. Moreover, we exhibit the potential of our approach for video amodal object segmentation tasks on FISHBOWL and our proposed MOViD-A. Project page at: http://jianxgao.github.io/C2F-Seg.

Abstract: Probabilistic Diffusion Models (PDMs) have recently emerged as a very promising class of generative models, achieving high performance in natural image generation. However, their performance relative to non-natural images, like radar-based satellite data, remains largely unknown. Generating large amounts of synthetic (and especially labelled) satellite data is crucial to implement deep-learning approaches for the processing and analysis of (interferometric) satellite aperture radar data. Here, we leverage PDMs to generate several radar-based satellite image datasets. We show that PDMs succeed in generating images with complex and realistic structures, but that sampling time remains an issue. Indeed, accelerated sampling strategies, which work well on simple image datasets like MNIST, fail on our radar datasets. We provide a simple and versatile open-source https://github.com/thomaskerdreux/PDM_SAR_InSAR_generation to train, sample and evaluate PDMs using any dataset on a single GPU.

Abstract: We investigate the applicability of quaternion-valued wavelets on the plane to holistic colour image processing. We present a methodology for decomposing and reconstructing colour images using quaternionic wavelet filters associated to recently developed quaternion-valued wavelets on the plane. We consider compression, enhancement, segmentation, and denoising techniques to demonstrate quaternion-valued wavelets as a promising tool for holistic colour image processing.

Abstract: Human-centric video frame interpolation has great potential for improving people's entertainment experiences and finding commercial applications in the sports analysis industry, e.g., synthesizing slow-motion videos. Although there are multiple benchmark datasets available in the community, none of them is dedicated for human-centric scenarios. To bridge this gap, we introduce SportsSloMo, a benchmark consisting of more than 130K video clips and 1M video frames of high-resolution ($\geq$720p) slow-motion sports videos crawled from YouTube. We re-train several state-of-the-art methods on our benchmark, and the results show a decrease in their accuracy compared to other datasets. It highlights the difficulty of our benchmark and suggests that it poses significant challenges even for the best-performing methods, as human bodies are highly deformable and occlusions are frequent in sports videos. To improve the accuracy, we introduce two loss terms considering the human-aware priors, where we add auxiliary supervision to panoptic segmentation and human keypoints detection, respectively. The loss terms are model agnostic and can be easily plugged into any video frame interpolation approaches. Experimental results validate the effectiveness of our proposed loss terms, leading to consistent performance improvement over 5 existing models, which establish strong baseline models on our benchmark. The dataset and code can be found at: https://neu-vi.github.io/SportsSlomo/.

Abstract: We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in the room such that the generated colors respect the hierarchical structure or semantic parts that are often composed of similar materials. Instead of applying flat stylization on the entire scene at a single step, we obtain weak semantic cues from geometric segmentation, which are further clarified by assigning initial colors to segmented parts. Then we add texture details for individual objects such that their projections on image space exhibit feature embedding aligned with the embedding of the input. The decomposition makes the entire pipeline tractable to a moderate amount of computation resources and memory. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated datasets with high-quality textures designed by skillful artists. To the best of our knowledge, it is the first practical and scalable approach that can create detailed and realistic textures of the desired style that maintain structural context for scenes with multiple objects.

Abstract: Large vision-language models (LVLMs) have recently witnessed rapid advancements, exhibiting a remarkable capacity for perceiving, understanding, and processing visual information by connecting visual receptor with large language models (LLMs). However, current assessments mainly focus on recognizing and reasoning abilities, lacking direct evaluation of conversational skills and neglecting visual storytelling abilities. In this paper, we propose an evaluation method that uses strong LLMs as judges to comprehensively evaluate the various abilities of LVLMs. Firstly, we construct a comprehensive visual dialogue dataset TouchStone, consisting of open-world images and questions, covering five major categories of abilities and 27 subtasks. This dataset not only covers fundamental recognition and comprehension but also extends to literary creation. Secondly, by integrating detailed image annotations we effectively transform the multimodal input content into a form understandable by LLMs. This enables us to employ advanced LLMs for directly evaluating the quality of the multimodal dialogue without requiring human intervention. Through validation, we demonstrate that powerful LVLMs, such as GPT-4, can effectively score dialogue quality by leveraging their textual capabilities alone, aligning with human preferences. We hope our work can serve as a touchstone for LVLMs' evaluation and pave the way for building stronger LVLMs. The evaluation code is available at https://github.com/OFA-Sys/TouchStone.

Abstract: We present EMDB, the Electromagnetic Database of Global 3D Human Pose and Shape in the Wild. EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape parameters with global body and camera trajectories for in-the-wild videos. We use body-worn, wireless electromagnetic (EM) sensors and a hand-held iPhone to record a total of 58 minutes of motion data, distributed over 81 indoor and outdoor sequences and 10 participants. Together with accurate body poses and shapes, we also provide global camera poses and body root trajectories. To construct EMDB, we propose a multi-stage optimization procedure, which first fits SMPL to the 6-DoF EM measurements and then refines the poses via image observations. To achieve high-quality results, we leverage a neural implicit avatar model to reconstruct detailed human surface geometry and appearance, which allows for improved alignment and smoothness via a dense pixel-level objective. Our evaluations, conducted with a multi-view volumetric capture system, indicate that EMDB has an expected accuracy of 2.3 cm positional and 10.6 degrees angular error, surpassing the accuracy of previous in-the-wild datasets. We evaluate existing state-of-the-art monocular RGB methods for camera-relative and global pose estimation on EMDB. EMDB is publicly available under https://ait.ethz.ch/emdb

Abstract: Semantic segmentation in autonomous driving has been undergoing an evolution from sparse point segmentation to dense voxel segmentation, where the objective is to predict the semantic occupancy of each voxel in the concerned 3D space. The dense nature of the prediction space has rendered existing efficient 2D-projection-based methods (e.g., bird's eye view, range view, etc.) ineffective, as they can only describe a subspace of the 3D scene. To address this, we propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively and a PointOcc model to process them efficiently. Considering the distance distribution of LiDAR point clouds, we construct the tri-perspective view in the cylindrical coordinate system for more fine-grained modeling of nearer areas. We employ spatial group pooling to maintain structural details during projection and adopt 2D backbones to efficiently process each TPV plane. Finally, we obtain the features of each point by aggregating its projected features on each of the processed TPV planes without the need for any post-processing. Extensive experiments on both 3D occupancy prediction and LiDAR segmentation benchmarks demonstrate that the proposed PointOcc achieves state-of-the-art performance with much faster speed. Specifically, despite only using LiDAR, PointOcc significantly outperforms all other methods, including multi-modal methods, with a large margin on the OpenOccupancy benchmark. Code: https://github.com/wzzheng/PointOcc.

Abstract: This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most existing research on HOI synthesis lacks comprehensive whole-body interactions with dynamic objects, e.g., often limited to manipulating small or static objects. Our task is significantly more challenging, as it requires modeling dynamic objects with various shapes, capturing whole-body motion, and ensuring physically valid interactions. To this end, we propose InterDiff, a framework comprising two key steps: (i) interaction diffusion, where we leverage a diffusion model to encode the distribution of future human-object interactions; (ii) interaction correction, where we introduce a physics-informed predictor to correct denoised HOIs in a diffusion step. Our key insight is to inject prior knowledge that the interactions under reference with respect to contact points follow a simple pattern and are easily predictable. Experiments on multiple human-object interaction datasets demonstrate the effectiveness of our method for this task, capable of producing realistic, vivid, and remarkably long-term 3D HOI predictions.

Abstract: In this paper, we introduce a novel approach to fine-grained cross-view geo-localization. Our method aligns a warped ground image with a corresponding GPS-tagged satellite image covering the same area using homography estimation. We first employ a differentiable spherical transform, adhering to geometric principles, to accurately align the perspective of the ground image with the satellite map. This transformation effectively places ground and aerial images in the same view and on the same plane, reducing the task to an image alignment problem. To address challenges such as occlusion, small overlapping range, and seasonal variations, we propose a robust correlation-aware homography estimator to align similar parts of the transformed ground image with the satellite image. Our method achieves sub-pixel resolution and meter-level GPS accuracy by mapping the center point of the transformed ground image to the satellite image using a homography matrix and determining the orientation of the ground camera using a point above the central axis. Operating at a speed of 30 FPS, our method outperforms state-of-the-art techniques, reducing the mean metric localization error by 21.3% and 32.4% in same-area and cross-area generalization tasks on the VIGOR benchmark, respectively, and by 34.4% on the KITTI benchmark in same-area evaluation.

Abstract: Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for high-quality frame synthesis and focused on motion generator design. The motion generator is trained in an autoregressive manner using heavy 3D convolutional discriminators to ensure motion coherence during video generation. In this paper, we introduce a novel motion generator design that uses a learning-based inversion network for GAN. The encoder in our method captures rich and smooth priors from encoding images to latents, and given the latent of an initially generated frame as guidance, our method can generate smooth future latent by modulating the inversion encoder temporally. Our method enjoys the advantage of sparse training and naturally constrains the generation space of our motion generator with the inversion network guided by the initial frame, eliminating the need for heavy discriminators. Moreover, our method supports style transfer with simple fine-tuning when the encoder is paired with a pretrained StyleGAN generator. Extensive experiments conducted on various benchmarks demonstrate the superiority of our method in generating long and high-resolution videos with decent single-frame quality and temporal consistency.

Abstract: The unprecedented advancements in Large Language Models (LLMs) have created a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding. This paper introduces PointLLM, a preliminary effort to fill this gap, thereby enabling LLMs to understand point clouds and offering a new avenue beyond 2D visual data. PointLLM processes colored object point clouds with human instructions and generates contextually appropriate responses, illustrating its grasp of point clouds and common sense. Specifically, it leverages a point cloud encoder with a powerful LLM to effectively fuse geometric, appearance, and linguistic information. We collect a novel dataset comprising 660K simple and 70K complex point-text instruction pairs to enable a two-stage training strategy: initially aligning latent spaces and subsequently instruction-tuning the unified model. To rigorously evaluate our model's perceptual abilities and its generalization capabilities, we establish two benchmarks: Generative 3D Object Classification and 3D Object Captioning, assessed through three different methods, including human evaluation, GPT-4/ChatGPT evaluation, and traditional metrics. Experiment results show that PointLLM demonstrates superior performance over existing 2D baselines. Remarkably, in human-evaluated object captioning tasks, PointLLM outperforms human annotators in over 50% of the samples. Codes, datasets, and benchmarks are available at https://github.com/OpenRobotLab/PointLLM .