Computer Vision and Pattern Recognition (cs.CV)

Abstract: Using multiple spatial modalities has been proven helpful in improving semantic segmentation performance. However, there are several real-world challenges that have yet to be addressed: (a) improving label efficiency and (b) enhancing robustness in realistic scenarios where modalities are missing at the test time. To address these challenges, we first propose a simple yet efficient multi-modal fusion mechanism Linear Fusion, that performs better than the state-of-the-art multi-modal models even with limited supervision. Second, we propose M3L: Multi-modal Teacher for Masked Modality Learning, a semi-supervised framework that not only improves the multi-modal performance but also makes the model robust to the realistic missing modality scenario using unlabeled data. We create the first benchmark for semi-supervised multi-modal semantic segmentation and also report the robustness to missing modalities. Our proposal shows an absolute improvement of up to 10% on robust mIoU above the most competitive baselines. Our code is available at https://github.com/harshm121/M3L

Abstract: Visual information extraction (VIE) plays an important role in Document Intelligence. Generally, it is divided into two tasks: semantic entity recognition (SER) and relation extraction (RE). Recently, pre-trained models for documents have achieved substantial progress in VIE, particularly in SER. However, most of the existing models learn the geometric representation in an implicit way, which has been found insufficient for the RE task since geometric information is especially crucial for RE. Moreover, we reveal another factor that limits the performance of RE lies in the objective gap between the pre-training phase and the fine-tuning phase for RE. To tackle these issues, we propose in this paper a multi-modal framework, named GeoLayoutLM, for VIE. GeoLayoutLM explicitly models the geometric relations in pre-training, which we call geometric pre-training. Geometric pre-training is achieved by three specially designed geometry-related pre-training tasks. Additionally, novel relation heads, which are pre-trained by the geometric pre-training tasks and fine-tuned for RE, are elaborately designed to enrich and enhance the feature representation. According to extensive experiments on standard VIE benchmarks, GeoLayoutLM achieves highly competitive scores in the SER task and significantly outperforms the previous state-of-the-arts for RE (\eg, the F1 score of RE on FUNSD is boosted from 80.35\% to 89.45\%). The code and models are publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/GeoLayoutLM

Abstract: Semi-Supervised Domain Adaptation (SSDA) is a recently emerging research topic that extends from the widely-investigated Unsupervised Domain Adaptation (UDA) by further having a few target samples labeled, i.e., the model is trained with labeled source samples, unlabeled target samples as well as a few labeled target samples. Compared with UDA, the key to SSDA lies how to most effectively utilize the few labeled target samples. Existing SSDA approaches simply merge the few precious labeled target samples into vast labeled source samples or further align them, which dilutes the value of labeled target samples and thus still obtains a biased model. To remedy this, in this paper, we propose to decouple SSDA as an UDA problem and a semi-supervised learning problem where we first learn an UDA model using labeled source and unlabeled target samples and then adapt the learned UDA model in a semi-supervised way using labeled and unlabeled target samples. By utilizing the labeled source samples and target samples separately, the bias problem can be well mitigated. We further propose a consistency learning based mean teacher model to effectively adapt the learned UDA model using labeled and unlabeled target samples. Experiments show our approach outperforms existing methods.

Abstract: Hyperbolic geometry, a Riemannian manifold endowed with constant sectional negative curvature, has been considered an alternative embedding space in many learning scenarios, \eg, natural language processing, graph learning, \etc, as a result of its intriguing property of encoding the data's hierarchical structure (like irregular graph or tree-likeness data). Recent studies prove that such data hierarchy also exists in the visual dataset, and investigate the successful practice of hyperbolic geometry in the computer vision (CV) regime, ranging from the classical image classification to advanced model adaptation learning. This paper presents the first and most up-to-date literature review of hyperbolic spaces for CV applications. To this end, we first introduce the background of hyperbolic geometry, followed by a comprehensive investigation of algorithms, with geometric prior of hyperbolic space, in the context of visual applications. We also conclude this manuscript and identify possible future directions.

Abstract: Detection of human body and its parts (e.g., head or hands) has been intensively studied. However, most of these CNNs-based detectors are trained independently, making it difficult to associate detected parts with body. In this paper, we focus on the joint detection of human body and its corresponding parts. Specifically, we propose a novel extended object representation integrating center-offsets of body parts, and construct a dense one-stage generic Body-Part Joint Detector (BPJDet). In this way, body-part associations are neatly embedded in a unified object representation containing both semantic and geometric contents. Therefore, we can perform multi-loss optimizations to tackle multi-tasks synergistically. BPJDet does not suffer from error-prone post matching, and keeps a better trade-off between speed and accuracy. Furthermore, BPJDet can be generalized to detect any one or more body parts. To verify the superiority of BPJDet, we conduct experiments on three body-part datasets (CityPersons, CrowdHuman and BodyHands) and one body-parts dataset COCOHumanParts. While keeping high detection accuracy, BPJDet achieves state-of-the-art association performance on all datasets comparing with its counterparts. Besides, we show benefits of advanced body-part association capability by improving performance of two representative downstream applications: accurate crowd head detection and hand contact estimation. Code is released in https://github.com/hnuzhy/BPJDet.

Abstract: Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale datasets. For most existing deep MVC methods, exploring the invariant representations of multiple views is still an intractable problem. In this paper, we propose a cross-view contrastive learning (CVCL) method that learns view-invariant representations and produces clustering results by contrasting the cluster assignments among multiple views. Specifically, we first employ deep autoencoders to extract view-dependent features in the pretraining stage. Then, a cluster-level CVCL strategy is presented to explore consistent semantic label information among the multiple views in the fine-tuning stage. Thus, the proposed CVCL method is able to produce more discriminative cluster assignments by virtue of this learning strategy. Moreover, we provide a theoretical analysis of soft cluster assignment alignment. Extensive experimental results obtained on several datasets demonstrate that the proposed CVCL method outperforms several state-of-the-art approaches.

Abstract: The Normalized Eight-Point algorithm has been widely viewed as the cornerstone in two-view geometry computation, where the seminal Hartley's normalization greatly improves the performance of the direct linear transformation (DLT) algorithm. A natural question is, whether there exists and how to find other normalization methods that may further improve the performance as per each input sample. In this paper, we provide a novel perspective and make two contributions towards this fundamental problem: 1) We revisit the normalized eight-point algorithm and make a theoretical contribution by showing the existence of different and better normalization algorithms; 2) We present a deep convolutional neural network with a self-supervised learning strategy to the normalization. Given eight pairs of correspondences, our network directly predicts the normalization matrices, thus learning to normalize each input sample. Our learning-based normalization module could be integrated with both traditional (e.g., RANSAC) and deep learning framework (affording good interpretability) with minimal efforts. Extensive experiments on both synthetic and real images show the effectiveness of our proposed approach.

Abstract: We introduce Omni-LOS, a neural computational imaging method for conducting holistic shape reconstruction (HSR) of complex objects utilizing a Single-Photon Avalanche Diode (SPAD)-based time-of-flight sensor. As illustrated in Fig. 1, our method enables new capabilities to reconstruct near-$360^\circ$ surrounding geometry of an object from a single scan spot. In such a scenario, traditional line-of-sight (LOS) imaging methods only see the front part of the object and typically fail to recover the occluded back regions. Inspired by recent advances of non-line-of-sight (NLOS) imaging techniques which have demonstrated great power to reconstruct occluded objects, Omni-LOS marries LOS and NLOS together, leveraging their complementary advantages to jointly recover the holistic shape of the object from a single scan position. The core of our method is to put the object nearby diffuse walls and augment the LOS scan in the front view with the NLOS scans from the surrounding walls, which serve as virtual ``mirrors'' to trap lights toward the object. Instead of separately recovering the LOS and NLOS signals, we adopt an implicit neural network to represent the object, analogous to NeRF and NeTF. While transients are measured along straight rays in LOS but over the spherical wavefronts in NLOS, we derive differentiable ray propagation models to simultaneously model both types of transient measurements so that the NLOS reconstruction also takes into account the direct LOS measurements and vice versa. We further develop a proof-of-concept Omni-LOS hardware prototype for real-world validation. Comprehensive experiments on various wall settings demonstrate that Omni-LOS successfully resolves shape ambiguities caused by occlusions, achieves high-fidelity 3D scan quality, and manages to recover objects of various scales and complexity.

Abstract: Endoscopic Ultrasound-Fine Needle Aspiration (EUS-FNA) is used to examine pancreatic cancer. EUS-FNA is an examination using EUS to insert a thin needle into the tumor and collect pancreatic tissue fragments. Then collected pancreatic tissue fragments are then stained to classify whether they are pancreatic cancer. However, staining and visual inspection are time consuming. In addition, if the pancreatic tissue fragment cannot be examined after staining, the collection must be done again on the other day. Therefore, our purpose is to classify from an unstained image whether it is available for examination or not, and to exceed the accuracy of visual classification by specialist physicians. Image classification before staining can reduce the time required for staining and the burden of patients. However, the images of pancreatic tissue fragments used in this study cannot be successfully classified by processing the entire image because the pancreatic tissue fragments are only a part of the image. Therefore, we propose a DeformableFormer that uses Deformable Convolution in MetaFormer framework. The architecture consists of a generalized model of the Vision Transformer, and we use Deformable Convolution in the TokenMixer part. In contrast to existing approaches, our proposed DeformableFormer is possible to perform feature extraction more locally and dynamically by Deformable Convolution. Therefore, it is possible to perform suitable feature extraction for classifying target. To evaluate our method, we classify two categories of pancreatic tissue fragments; available and unavailable for examination. We demonstrated that our method outperformed the accuracy by specialist physicians and conventional methods.

Abstract: Connected and cooperative driving requires precise calibration of the roadside infrastructure for having a reliable perception system. To solve this requirement in an automated manner, we present a robust extrinsic calibration method for automated geo-referenced camera calibration. Our method requires a calibration vehicle equipped with a combined GNSS/RTK receiver and an inertial measurement unit (IMU) for self-localization. In order to remove any requirements for the target's appearance and the local traffic conditions, we propose a novel approach using hypothesis filtering. Our method does not require any human interaction with the information recorded by both the infrastructure and the vehicle. Furthermore, we do not limit road access for other road users during calibration. We demonstrate the feasibility and accuracy of our approach by evaluating our approach on synthetic datasets as well as a real-world connected intersection, and deploying the calibration on real infrastructure. Our source code is publicly available.

Abstract: Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at \url{https://github.com/Vision-Intelligence-and-Robots-Group/count-anything}.

Abstract: Image-text retrieval, as a fundamental and important branch of information retrieval, has attracted extensive research attentions. The main challenge of this task is cross-modal semantic understanding and matching. Some recent works focus more on fine-grained cross-modal semantic matching. With the prevalence of large scale multimodal pretraining models, several state-of-the-art models (e.g. X-VLM) have achieved near-perfect performance on widely-used image-text retrieval benchmarks, i.e. MSCOCO-Test-5K and Flickr30K-Test-1K. In this paper, we review the two common benchmarks and observe that they are insufficient to assess the true capability of models on fine-grained cross-modal semantic matching. The reason is that a large amount of images and texts in the benchmarks are coarse-grained. Based on the observation, we renovate the coarse-grained images and texts in the old benchmarks and establish the improved benchmarks called MSCOCO-FG and Flickr30K-FG. Specifically, on the image side, we enlarge the original image pool by adopting more similar images. On the text side, we propose a novel semi-automatic renovation approach to refine coarse-grained sentences into finer-grained ones with little human effort. Furthermore, we evaluate representative image-text retrieval models on our new benchmarks to demonstrate the effectiveness of our method. We also analyze the capability of models on fine-grained semantic comprehension through extensive experiments. The results show that even the state-of-the-art models have much room for improvement in fine-grained semantic understanding, especially in distinguishing attributes of close objects in images. Our code and improved benchmark datasets are publicly available at: https://github.com/cwj1412/MSCOCO-Flikcr30K_FG, which we hope will inspire further in-depth research on cross-modal retrieval.

Abstract: Recall one time when we were in an unfamiliar mall. We might mistakenly think that there exists or does not exist a piece of glass in front of us. Such mistakes will remind us to walk more safely and freely at the same or a similar place next time. To absorb the human mistake correction wisdom, we propose a novel glass segmentation network to detect transparent glass, dubbed GlassSegNet. Motivated by this human behavior, GlassSegNet utilizes two key stages: the identification stage (IS) and the correction stage (CS). The IS is designed to simulate the detection procedure of human recognition for identifying transparent glass by global context and edge information. The CS then progressively refines the coarse prediction by correcting mistake regions based on gained experience. Extensive experiments show clear improvements of our GlassSegNet over thirty-four state-of-the-art methods on three benchmark datasets.

Abstract: Remote sensing image segmentation is a specific task of remote sensing image interpretation. A good remote sensing image segmentation algorithm can provide guidance for environmental protection, agricultural production, and urban construction. This paper proposes a new type of UNet image segmentation algorithm based on channel self attention mechanism and residual connection called . In my experiment, the new network model improved mIOU by 2.48% compared to traditional UNet on the FoodNet dataset. The image segmentation algorithm proposed in this article enhances the internal connections between different items in the image, thus achieving better segmentation results for remote sensing images with occlusion.

Abstract: Face clustering can provide pseudo-labels to the massive unlabeled face data and improve the performance of different face recognition models. The existing clustering methods generally aggregate the features within subgraphs that are often implemented based on a uniform threshold or a learned cutoff position. This may reduce the recall of subgraphs and hence degrade the clustering performance. This work proposed an efficient neighborhood-aware subgraph adjustment method that can significantly reduce the noise and improve the recall of the subgraphs, and hence can drive the distant nodes to converge towards the same centers. More specifically, the proposed method consists of two components, i.e. face embeddings enhancement using the embeddings from neighbors, and enclosed subgraph construction of node pairs for structural information extraction. The embeddings are combined to predict the linkage probabilities for all node pairs to replace the cosine similarities to produce new subgraphs that can be further used for aggregation of GCNs or other clustering methods. The proposed method is validated through extensive experiments against a range of clustering solutions using three benchmark datasets and numerical results confirm that it outperforms the SOTA solutions in terms of generalization capability.

Abstract: The advancement of computer vision and machine learning has made datasets a crucial element for further research and applications. However, the creation and development of robots with advanced recognition capabilities are hindered by the lack of appropriate datasets. Existing image or video processing datasets are unable to accurately depict observations from a moving robot, and they do not contain the kinematics information necessary for robotic tasks. Synthetic data, on the other hand, are cost-effective to create and offer greater flexibility for adapting to various applications. Hence, they are widely utilized in both research and industry. In this paper, we propose the dataset HabitatDyn, which contains both synthetic RGB videos, semantic labels, and depth information, as well as kinetics information. HabitatDyn was created from the perspective of a mobile robot with a moving camera, and contains 30 scenes featuring six different types of moving objects with varying velocities. To demonstrate the usability of our dataset, two existing algorithms are used for evaluation and an approach to estimate the distance between the object and camera is implemented based on these segmentation methods and evaluated through the dataset. With the availability of this dataset, we aspire to foster further advancements in the field of mobile robotics, leading to more capable and intelligent robots that can navigate and interact with their environments more effectively. The code is publicly available at https://github.com/ignc-research/HabitatDyn.

Abstract: The research community has witnessed the powerful potential of self-supervised Masked Image Modeling (MIM), which enables the models capable of learning visual representation from unlabeled data. In this paper, to incorporate both the crucial global structural information and local details for dense prediction tasks, we alter the perspective to the frequency domain and present a new MIM-based framework named FreMAE for self-supervised pre-training for medical image segmentation. Based on the observations that the detailed structural information mainly lies in the high-frequency components and the high-level semantics are abundant in the low-frequency counterparts, we further incorporate multi-stage supervision to guide the representation learning during the pre-training phase. Extensive experiments on three benchmark datasets show the superior advantage of our proposed FreMAE over previous state-of-the-art MIM methods. Compared with various baselines trained from scratch, our FreMAE could consistently bring considerable improvements to the model performance. To the best our knowledge, this is the first attempt towards MIM with Fourier Transform in medical image segmentation.

Abstract: For years Single Image Super resolution(SISR) is an interesting and ill posed problem in Computer Vision. The traditional Super Resolution(SR) imaging approaches involve Interpolation, Reconstruction and Learning based methods. Interpolation methods are fast and uncomplicated to compute but they are not so accurate and reliable. Reconstruction based methods are better compared with Interpolation methods but are time consuming and quality degrades as the scaling increases. Even though, Learning based methods like Markov random chain are far better then all the previous they are unable to match the performance of deep learning models for SISR. In this project, Residual Dense Networks architecture proposed by Yhang et al \cite{srrdn} was extended to involve novel components and the importance of components in this architecture will be analysed. This architecture makes full use of hierarchial features from original low-resolution (LR) images to achieve higher performance. The network structure consists of four main blocks. The core of the architecture is the residual dense block(RDB) where the local features are extracted and made use of via dense convolutional layers. In this work, investigation of each block was performed and effect of each modules was be studied and analyzed. Analyses by use various loss metric was also carried out in this project. Also a comparison was made with various state of the art models which highly differ by architecture and components. The modules in the model were be built from scratch and were trained and tested. The training and testing was be carried out for various scaling factors and the performance was be evaluated.

Abstract: Deep learning based medical volumetric segmentation methods either train the model from scratch or follow the standard "pre-training then finetuning" paradigm. Although finetuning a well pre-trained model on downstream tasks can harness its representation power, the standard full finetuning is costly in terms of computation and memory footprint. In this paper, we present the first study on parameter-efficient transfer learning for medical volumetric segmentation and propose a novel framework named Med-Tuning based on intra-stage feature enhancement and inter-stage feature interaction. Given a large-scale pre-trained model on 2D natural images, our method can exploit both the multi-scale spatial feature representations and temporal correlations along image slices, which are crucial for accurate medical volumetric segmentation. Extensive experiments on three benchmark datasets (including CT and MRI) show that our method can achieve better results than previous state-of-the-art parameter-efficient transfer learning methods and full finetuning for the segmentation task, with much less tuned parameter costs. Compared to full finetuning, our method reduces the finetuned model parameters by up to 4x, with even better segmentation performance.

Abstract: Natural language (NL) based vehicle retrieval is a task aiming to retrieve a vehicle that is most consistent with a given NL query from among all candidate vehicles. Because NL query can be easily obtained, such a task has a promising prospect in building an interactive intelligent traffic system (ITS). Current solutions mainly focus on extracting both text and image features and mapping them to the same latent space to compare the similarity. However, existing methods usually use dependency analysis or semantic role-labelling techniques to find keywords related to vehicle attributes. These techniques may require a lot of pre-processing and post-processing work, and also suffer from extracting the wrong keyword when the NL query is complex. To tackle these problems and simplify, we borrow the idea from named entity recognition (NER) and construct FindVehicle, a NER dataset in the traffic domain. It has 42.3k labelled NL descriptions of vehicle tracks, containing information such as the location, orientation, type and colour of the vehicle. FindVehicle also adopts both overlapping entities and fine-grained entities to meet further requirements. To verify its effectiveness, we propose a baseline NL-based vehicle retrieval model called VehicleFinder. Our experiment shows that by using text encoders pre-trained by FindVehicle, VehicleFinder achieves 87.7\% precision and 89.4\% recall when retrieving a target vehicle by text command on our homemade dataset based on UA-DETRAC. The time cost of VehicleFinder is 279.35 ms on one ARM v8.2 CPU and 93.72 ms on one RTX A4000 GPU, which is much faster than the Transformer-based system. The dataset is open-source via the link https://github.com/GuanRunwei/FindVehicle, and the implementation can be found via the link https://github.com/GuanRunwei/VehicleFinder-CTIM.

Abstract: Deep metric learning aims to construct an embedding space where samples of the same class are close to each other, while samples of different classes are far away from each other. Most existing deep metric learning methods attempt to maximize the difference of inter-class features. And semantic related information is obtained by increasing the distance between samples of different classes in the embedding space. However, compressing all positive samples together while creating large margins between different classes unconsciously destroys the local structure between similar samples. Ignoring the intra-class variance contained in the local structure between similar samples, the embedding space obtained from training receives lower generalizability over unseen classes, which would lead to the network overfitting the training set and crashing on the test set. To address these considerations, this paper designs a self-supervised generative assisted ranking framework that provides a semi-supervised view of intra-class variance learning scheme for typical supervised deep metric learning. Specifically, this paper performs sample synthesis with different intensities and diversity for samples satisfying certain conditions to simulate the complex transformation of intra-class samples. And an intra-class ranking loss function is designed using the idea of self-supervised learning to constrain the network to maintain the intra-class distribution during the training process to capture the subtle intra-class variance. With this approach, a more realistic embedding space can be obtained in which global and local structures of samples are well preserved, thus enhancing the effectiveness of downstream tasks. Extensive experiments on four benchmarks have shown that this approach surpasses state-of-the-art methods

Abstract: A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is significantly more challenging in the presence of multiple moving and/or deforming objects. Traditional methods have approached the setup with a mix of simplifications, scene priors, pretrained templates, or known deformation models. The advent of neural representations, especially neural implicit representations and radiance fields, opens the possibility of end-to-end optimization to collectively capture geometry, appearance, and object motion. However, current approaches produce global scene encoding, assume multiview capture with limited or no motion in the scenes, and do not facilitate easy manipulation beyond novel view synthesis. In this work, we introduce a factored neural scene representation that can directly be learned from a monocular RGB-D video to produce object-level neural presentations with an explicit encoding of object movement (e.g., rigid trajectory) and/or deformations (e.g., nonrigid movement). We evaluate ours against a set of neural approaches on both synthetic and real data to demonstrate that the representation is efficient, interpretable, and editable (e.g., change object trajectory). The project webpage is available at: $\href{https://yushiangw.github.io/factorednerf/}{\text{link}}$.

Abstract: Image colorization has been attracting the research interests of the community for decades. However, existing methods still struggle to provide satisfactory colorized results given grayscale images due to a lack of human-like global understanding of colors. Recently, large-scale Text-to-Image (T2I) models have been exploited to transfer the semantic information from the text prompts to the image domain, where text provides a global control for semantic objects in the image. In this work, we introduce a colorization model piggybacking on the existing powerful T2I diffusion model. Our key idea is to exploit the color prior knowledge in the pre-trained T2I diffusion model for realistic and diverse colorization. A diffusion guider is designed to incorporate the pre-trained weights of the latent diffusion model to output a latent color prior that conforms to the visual semantics of the grayscale input. A lightness-aware VQVAE will then generate the colorized result with pixel-perfect alignment to the given grayscale image. Our model can also achieve conditional colorization with additional inputs (e.g. user hints and texts). Extensive experiments show that our method achieves state-of-the-art performance in terms of perceptual quality.

Abstract: High-quality reconstruction of controllable 3D head avatars from 2D videos is highly desirable for virtual human applications in movies, games, and telepresence. Neural implicit fields provide a powerful representation to model 3D head avatars with personalized shape, expressions, and facial parts, e.g., hair and mouth interior, that go beyond the linear 3D morphable model (3DMM). However, existing methods do not model faces with fine-scale facial features, or local control of facial parts that extrapolate asymmetric expressions from monocular videos. Further, most condition only on 3DMM parameters with poor(er) locality, and resolve local features with a global neural field. We build on part-based implicit shape models that decompose a global deformation field into local ones. Our novel formulation models multiple implicit deformation fields with local semantic rig-like control via 3DMM-based parameters, and representative facial landmarks. Further, we propose a local control loss and attention mask mechanism that promote sparsity of each learned deformation field. Our formulation renders sharper locally controllable nonlinear deformations than previous implicit monocular approaches, especially mouth interior, asymmetric expressions, and facial details.

Abstract: Mixed reality applications require tracking the user's full-body motion to enable an immersive experience. However, typical head-mounted devices can only track head and hand movements, leading to a limited reconstruction of full-body motion due to variability in lower body configurations. We propose BoDiffusion -- a generative diffusion model for motion synthesis to tackle this under-constrained reconstruction problem. We present a time and space conditioning scheme that allows BoDiffusion to leverage sparse tracking inputs while generating smooth and realistic full-body motion sequences. To the best of our knowledge, this is the first approach that uses the reverse diffusion process to model full-body tracking as a conditional sequence generation task. We conduct experiments on the large-scale motion-capture dataset AMASS and show that our approach outperforms the state-of-the-art approaches by a significant margin in terms of full-body motion realism and joint reconstruction error.

Abstract: Purpose: In some proton therapy facilities, patient alignment relies on two 2D orthogonal kV images, taken at fixed, oblique angles, as no 3D on-the-bed imaging is available. The visibility of the tumor in kV images is limited since the patient's 3D anatomy is projected onto a 2D plane, especially when the tumor is behind high-density structures such as bones. This can lead to large patient setup errors. A solution is to reconstruct the 3D CT image from the kV images obtained at the treatment isocenter in the treatment position. Methods: An asymmetric autoencoder-like network built with vision-transformer blocks was developed. The data was collected from 1 head and neck patient: 2 orthogonal kV images (1024x1024 voxels), 1 3D CT with padding (512x512x512) acquired from the in-room CT-on-rails before kVs were taken and 2 digitally-reconstructed-radiograph (DRR) images (512x512) based on the CT. We resampled kV images every 8 voxels and DRR and CT every 4 voxels, thus formed a dataset consisting of 262,144 samples, in which the images have a dimension of 128 for each direction. In training, both kV and DRR images were utilized, and the encoder was encouraged to learn the jointed feature map from both kV and DRR images. In testing, only independent kV images were used. The full-size synthetic CT (sCT) was achieved by concatenating the sCTs generated by the model according to their spatial information. The image quality of the synthetic CT (sCT) was evaluated using mean absolute error (MAE) and per-voxel-absolute-CT-number-difference volume histogram (CDVH). Results: The model achieved a speed of 2.1s and a MAE of <40HU. The CDVH showed that <5% of the voxels had a per-voxel-absolute-CT-number-difference larger than 185 HU. Conclusion: A patient-specific vision-transformer-based network was developed and shown to be accurate and efficient to reconstruct 3D CT images from kV images.

Abstract: Recently, tensor singular value decomposition (t-SVD) has emerged as a promising tool for hyperspectral image (HSI) processing. In the t-SVD, there are two key building blocks: (i) the low-rank enhanced transform and (ii) the accompanying low-rank characterization of transformed frontal slices. Previous t-SVD methods mainly focus on the developments of (i), while neglecting the other important aspect, i.e., the exact characterization of transformed frontal slices. In this letter, we exploit the potentiality in both building blocks by leveraging the \underline{\bf H}ierarchical nonlinear transform and the \underline{\bf H}ierarchical matrix factorization to establish a new \underline{\bf T}ensor \underline{\bf F}actorization (termed as H2TF). Compared to shallow counter partners, e.g., low-rank matrix factorization or its convex surrogates, H2TF can better capture complex structures of transformed frontal slices due to its hierarchical modeling abilities. We then suggest the H2TF-based HSI denoising model and develop an alternating direction method of multipliers-based algorithm to address the resultant model. Extensive experiments validate the superiority of our method over state-of-the-art HSI denoising methods.