Xin Li

Xin Li, Tao Ma, Yuenan Hou et al. · stanford

LiDAR-camera fusion methods have shown impressive performance in 3D object detection. Recent advanced multi-modal methods mainly perform global fusion, where image features and point cloud features are fused across the whole scene. Such practice lacks fine-grained region-level information, yielding suboptimal fusion performance. In this paper, we present the novel Local-to-Global fusion network (LoGoNet), which performs LiDAR-camera fusion at both local and global levels. Concretely, the Global Fusion (GoF) of LoGoNet is built upon previous literature, while we exclusively use point centroids to more precisely represent the position of voxel features, thus achieving better cross-modal alignment. As to the Local Fusion (LoF), we first divide each proposal into uniform grids and then project these grid centers to the images. The image features around the projected grid points are sampled to be fused with position-decorated point cloud features, maximally utilizing the rich contextual information around the proposals. The Feature Dynamic Aggregation (FDA) module is further proposed to achieve information interaction between these locally and globally fused features, thus producing more informative multi-modal features. Extensive experiments on both Waymo Open Dataset (WOD) and KITTI datasets show that LoGoNet outperforms all state-of-the-art 3D detection methods. Notably, LoGoNet ranks 1st on Waymo 3D object detection leaderboard and obtains 81.02 mAPH (L2) detection performance. It is noteworthy that, for the first time, the detection performance on three classes surpasses 80 APH (L2) simultaneously. Code will be available at \url{https://github.com/sankin97/LoGoNet}.

Jiahui Yu, Yuanzhong Xu, Jing Yu Koh et al. · cmu

We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge. Parti treats text-to-image generation as a sequence-to-sequence modeling problem, akin to machine translation, with sequences of image tokens as the target outputs rather than text tokens in another language. This strategy can naturally tap into the rich body of prior work on large language models, which have seen continued advances in capabilities and performance through scaling data and model sizes. Our approach is simple: First, Parti uses a Transformer-based image tokenizer, ViT-VQGAN, to encode images as sequences of discrete tokens. Second, we achieve consistent quality improvements by scaling the encoder-decoder Transformer model up to 20B parameters, with a new state-of-the-art zero-shot FID score of 7.23 and finetuned FID score of 3.22 on MS-COCO. Our detailed analysis on Localized Narratives as well as PartiPrompts (P2), a new holistic benchmark of over 1600 English prompts, demonstrate the effectiveness of Parti across a wide variety of categories and difficulty aspects. We also explore and highlight limitations of our models in order to define and exemplify key areas of focus for further improvements. See https://parti.research.google/ for high-resolution images.

Qiuhong Shen, Lei Qiao, Jinyang Guo et al.

Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.

Tao Ma, Xuemeng Yang, Hongbin Zhou et al. · stanford

Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds. We have found that the full potential of offboard 3D detectors is not explored mainly due to two reasons: (1) the onboard multi-object tracker cannot generate sufficient complete object trajectories, and (2) the motion state of objects poses an inevitable challenge for the object-centric refining stage in leveraging the long-term temporal context representation. To tackle these problems, we propose a novel paradigm of offboard 3D object detection, named DetZero. Concretely, an offline tracker coupled with a multi-frame detector is proposed to focus on the completeness of generated object tracks. An attention-mechanism refining module is proposed to strengthen contextual information interaction across long-term sequential point clouds for object refining with decomposed regression methods. Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods. Notably, DetZero ranks 1st place on Waymo 3D object detection leaderboard with 85.15 mAPH (L2) detection performance. Further experiments validate the application of taking the place of human labels with such high-quality results. Our empirical study leads to rethinking conventions and interesting findings that can guide future research on offboard 3D object detection.

Xin Yang, Yi Lin, Zhiwei Wang et al.

In this paper, we propose a bi-modality medical image synthesis approach based on sequential generative adversarial network (GAN) and semi-supervised learning. Our approach consists of two generative modules that synthesize images of the two modalities in a sequential order. A method for measuring the synthesis complexity is proposed to automatically determine the synthesis order in our sequential GAN. Images of the modality with a lower complexity are synthesized first, and the counterparts with a higher complexity are generated later. Our sequential GAN is trained end-to-end in a semi-supervised manner. In supervised training, the joint distribution of bi-modality images are learned from real paired images of the two modalities by explicitly minimizing the reconstruction losses between the real and synthetic images. To avoid overfitting limited training images, in unsupervised training, the marginal distribution of each modality is learned based on unpaired images by minimizing the Wasserstein distance between the distributions of real and fake images. We comprehensively evaluate the proposed model using two synthesis tasks based on three types of evaluate metrics and user studies. Visual and quantitative results demonstrate the superiority of our method to the state-of-the-art methods, and reasonable visual quality and clinical significance. Code is made publicly available at https://github.com/hustlinyi/Multimodal-Medical-Image-Synthesis.

Hai Wu, Chenglu Wen, Shaoshuai Shi et al.

Recently, virtual/pseudo-point-based 3D object detection that seamlessly fuses RGB images and LiDAR data by depth completion has gained great attention. However, virtual points generated from an image are very dense, introducing a huge amount of redundant computation during detection. Meanwhile, noises brought by inaccurate depth completion significantly degrade detection precision. This paper proposes a fast yet effective backbone, termed VirConvNet, based on a new operator VirConv (Virtual Sparse Convolution), for virtual-point-based 3D object detection. VirConv consists of two key designs: (1) StVD (Stochastic Voxel Discard) and (2) NRConv (Noise-Resistant Submanifold Convolution). StVD alleviates the computation problem by discarding large amounts of nearby redundant voxels. NRConv tackles the noise problem by encoding voxel features in both 2D image and 3D LiDAR space. By integrating VirConv, we first develop an efficient pipeline VirConv-L based on an early fusion design. Then, we build a high-precision pipeline VirConv-T based on a transformed refinement scheme. Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework. On the KITTI car 3D detection test leaderboard, our VirConv-L achieves 85% AP with a fast running speed of 56ms. Our VirConv-T and VirConv-S attains a high-precision of 86.3% and 87.2% AP, and currently rank 2nd and 1st, respectively. The code is available at https://github.com/hailanyi/VirConv.

Yili Wang, Xin Li, Kun Xu et al.

We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. To reflect the homomorphism property of color operators, we employ equivariant mapping and adopt an encoder-decoder structure which maps the non-linear color transformation to a much simpler transformation (i.e., translation) in a high dimensional space. The scalar strength of each neural color operator is predicted using CNN based strength predictors by analyzing global image statistics. Overall, our method is rather lightweight and offers flexible controls. Experiments and user studies on public datasets show that our method consistently achieves the best results compared with SOTA methods in both quantitative measures and visual qualities. The code and pretrained models are provided at https://github.com/amberwangyili/neurop

Hang Zhang, Xin Li, Lidong Bing

We present Video-LLaMA a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen pre-trained visual and audio encoders and the frozen LLMs. Unlike previous works that complement LLMs to process the visual or audio signals only, Video-LLaMA enables video comprehension by tackling two challenges: (1) capturing the temporal changes in visual scenes, (2) integrating audio-visual signals. To counter the first challenge, we propose a Video Q-former to assemble a pre-trained image encoder into our video encoder and introduce a video-to-text generation task to learn video-language correspondence. For the second challenge, we leverage ImageBind, a universal embedding model aligning multiple modalities, as the pre-trained audio encoder and introduce an Audio Q-former on top of ImageBind to learn reasonable auditory query embeddings for the LLM module. To align the output of both visual and audio encoders with LLM's embedding space, we first train Video-LLaMA on massive video/image-caption pairs and then tune our model with visual-instruction datasets of moderate amount but higher quality. We found Video-LLaMA shows the ability to perceive and comprehend video content and generate meaningful responses grounded in the visual and auditory information presented in the videos.

Yongxin Zhu, Zhen Liu, Yukang Liang et al. · tencent-ai

In this paper, we propose a novel multi-modal framework for Scene Text Visual Question Answering (STVQA), which requires models to read scene text in images for question answering. Apart from text or visual objects, which could exist independently, scene text naturally links text and visual modalities together by conveying linguistic semantics while being a visual object in an image simultaneously. Different to conventional STVQA models which take the linguistic semantics and visual semantics in scene text as two separate features, in this paper, we propose a paradigm of "Locate Then Generate" (LTG), which explicitly unifies this two semantics with the spatial bounding box as a bridge connecting them. Specifically, at first, LTG locates the region in an image that may contain the answer words with an answer location module (ALM) consisting of a region proposal network and a language refinement network, both of which can transform to each other with one-to-one mapping via the scene text bounding box. Next, given the answer words selected by ALM, LTG generates a readable answer sequence with an answer generation module (AGM) based on a pre-trained language model. As a benefit of the explicit alignment of the visual and linguistic semantics, even without any scene text based pre-training tasks, LTG can boost the absolute accuracy by +6.06% and +6.92% on the TextVQA dataset and the ST-VQA dataset respectively, compared with a non-pre-training baseline. We further demonstrate that LTG effectively unifies visual and text modalities through the spatial bounding box connection, which is underappreciated in previous methods.

Xin Li, Yuqing Huang, Zhenyu He et al.

Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking. However, a single image patch cannot provide a complete and precise concept of the target object as images are limited in their ability to abstract and can be ambiguous, which makes it difficult to track targets with drastic variations. In this paper, we propose the CiteTracker to enhance target modeling and inference in visual tracking by connecting images and text. Specifically, we develop a text generation module to convert the target image patch into a descriptive text containing its class and attribute information, providing a comprehensive reference point for the target. In addition, a dynamic description module is designed to adapt to target variations for more effective target representation. We then associate the target description and the search image using an attention-based correlation module to generate the correlated features for target state reference. Extensive experiments on five diverse datasets are conducted to evaluate the proposed algorithm and the favorable performance against the state-of-the-art methods demonstrates the effectiveness of the proposed tracking method.

Zhaoyang Xia, Youquan Liu, Xin Li et al.

Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inherent label noise for moving objects. To address the above-mentioned problems, we propose the following three solutions: 1) Redesigning the completion sub-network. We design a novel completion sub-network, which consists of several Multi-Path Blocks (MPBs) to aggregate multi-scale features and is free from the lossy downsampling operations. 2) Distilling rich knowledge from the multi-frame model. We design a novel knowledge distillation objective, dubbed Dense-to-Sparse Knowledge Distillation (DSKD). It transfers the dense, relation-based semantic knowledge from the multi-frame teacher to the single-frame student, significantly improving the representation learning of the single-frame model. 3) Completion label rectification. We propose a simple yet effective label rectification strategy, which uses off-the-shelf panoptic segmentation labels to remove the traces of dynamic objects in completion labels, greatly improving the performance of deep models especially for those moving objects. Extensive experiments are conducted in two public SSC benchmarks, i.e., SemanticKITTI and SemanticPOSS. Our SCPNet ranks 1st on SemanticKITTI semantic scene completion challenge and surpasses the competitive S3CNet by 7.2 mIoU. SCPNet also outperforms previous completion algorithms on the SemanticPOSS dataset. Besides, our method also achieves competitive results on SemanticKITTI semantic segmentation tasks, showing that knowledge learned in the scene completion is beneficial to the segmentation task.

Hongchen Tan, Xiuping Liu, Baocai Yin et al.

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two novel modules: a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM). SDM combines the spatial self-attention mechanism and a new Semantic Disentangling Loss (SDL) to help the generator distill key semantic information for the image generation. DNM uses a Variational Auto-Encoder (VAE) to normalize and denoise the image latent distribution, which can help the discriminator better distinguish synthesized images from real images. DNM also adopts a Distribution Adversarial Loss (DAL) to guide the generator to align with normalized real image distributions in the latent space. Extensive experiments on two public datasets demonstrated that our DR-GAN achieved a competitive performance in the Text-to-Image task.

Hai Wu, Chenglu Wen, Wei Li et al.

3D object detection received increasing attention in autonomous driving recently. Objects in 3D scenes are distributed with diverse orientations. Ordinary detectors do not explicitly model the variations of rotation and reflection transformations. Consequently, large networks and extensive data augmentation are required for robust detection. Recent equivariant networks explicitly model the transformation variations by applying shared networks on multiple transformed point clouds, showing great potential in object geometry modeling. However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed. In this work, we present TED, an efficient Transformation-Equivariant 3D Detector to overcome the computation cost and speed issues. TED first applies a sparse convolution backbone to extract multi-channel transformation-equivariant voxel features; and then aligns and aggregates these equivariant features into lightweight and compact representations for high-performance 3D object detection. On the highly competitive KITTI 3D car detection leaderboard, TED ranked 1st among all submissions with competitive efficiency.

Lingdong Kong, Youquan Liu, Xin Li et al.

The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets often contain data that are meticulously cleaned. Such configurations, however, cannot reflect the reliability of perception models during the deployment stage. In this work, we present Robo3D, the first comprehensive benchmark heading toward probing the robustness of 3D detectors and segmentors under out-of-distribution scenarios against natural corruptions that occur in real-world environments. Specifically, we consider eight corruption types stemming from severe weather conditions, external disturbances, and internal sensor failure. We uncover that, although promising results have been progressively achieved on standard benchmarks, state-of-the-art 3D perception models are at risk of being vulnerable to corruptions. We draw key observations on the use of data representations, augmentation schemes, and training strategies, that could severely affect the model's performance. To pursue better robustness, we propose a density-insensitive training framework along with a simple flexible voxelization strategy to enhance the model resiliency. We hope our benchmark and approach could inspire future research in designing more robust and reliable 3D perception models. Our robustness benchmark suite is publicly available.

Hao Liu, Xinghua Jiang, Xin Li et al. · bytedance, tencent-ai

The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent ability of learning visual representation from unlabeled data. Aiming at learning representations with high semantics abstracted, a group of works attempts to reconstruct non-semantic pixels with large-ratio masking strategy, which may suffer from "over-smoothing" problem, while others directly infuse semantics into targets in off-line way requiring extra data. Different from them, we shift the perspective to the Fourier domain which naturally has global perspective and present a new Masked Image Modeling (MIM), termed Geminated Gestalt Autoencoder (Ge$^2$-AE) for visual pre-training. Specifically, we equip our model with geminated decoders in charge of reconstructing image contents from both pixel and frequency space, where each other serves as not only the complementation but also the reciprocal constraints. Through this way, more robust representations can be learned in the pre-trained encoders, of which the effectiveness is confirmed by the juxtaposing experimental results on downstream recognition tasks. We also conduct several quantitative and qualitative experiments to investigate the learning behavior of our method. To our best knowledge, this is the first MIM work to solve the visual pre-training through the lens of frequency domain.

Jiepeng Wang, Congyi Zhang, Peng Wang et al.

3D reconstruction techniques have widely been used for digital documentation of archaeological fragments. However, efficient digital capture of fragments remains as a challenge. In this work, we aim to develop a portable, high-throughput, and accurate reconstruction system for efficient digitization of fragments excavated in archaeological sites. To realize high-throughput digitization of large numbers of objects, an effective strategy is to perform scanning and reconstruction in batches. However, effective batch-based scanning and reconstruction face two key challenges: 1) how to correlate partial scans of the same object from multiple batch scans, and 2) how to register and reconstruct complete models from partial scans that exhibit only small overlaps. To tackle these two challenges, we develop a new batch-based matching algorithm that pairs the front and back sides of the fragments, and a new Bilateral Boundary ICP algorithm that can register partial scans sharing very narrow overlapping regions. Extensive validation in labs and testing in excavation sites demonstrate that these designs enable efficient batch-based scanning for fragments. We show that such a batch-based scanning and reconstruction pipeline can have immediate applications on digitizing sherds in archaeological excavations. Our project page: https://jiepengwang.github.io/FIRES/.

Renhong Zhang, Tianheng Cheng, Shusheng Yang et al.

Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tracking objects. To address those issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices. Firstly, MobileInst adopts a mobile vision transformer to extract multi-level semantic features and presents an efficient query-based dual-transformer instance decoder for mask kernels and a semantic-enhanced mask decoder to generate instance segmentation per frame. Secondly, MobileInst exploits simple yet effective kernel reuse and kernel association to track objects for video instance segmentation. Further, we propose temporal query passing to enhance the tracking ability for kernels. We conduct experiments on COCO and YouTube-VIS datasets to demonstrate the superiority of MobileInst and evaluate the inference latency on one single CPU core of Snapdragon 778G Mobile Platform, without other methods of acceleration. On the COCO dataset, MobileInst achieves 31.2 mask AP and 433 ms on the mobile CPU, which reduces the latency by 50% compared to the previous SOTA. For video instance segmentation, MobileInst achieves 35.0 AP on YouTube-VIS 2019 and 30.1 AP on YouTube-VIS 2021. Code will be available to facilitate real-world applications and future research.

Tianwei Lin, Honglin Lin, Fu Li et al. · amazon-science

Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have been achieved by recent deep models. However, deep neural network based methods are too expensive to run in real-time. Meanwhile, bilateral grid based methods are much faster but still contain artifacts like overexposure. In this work, we propose the \textbf{Adaptive ColorMLP (AdaCM)}, an effective and efficient framework for universal photo-realistic style transfer. First, we find the complex non-linear color mapping between input and target domain can be efficiently modeled by a small multi-layer perceptron (ColorMLP) model. Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair. Experimental results demonstrate that AdaCM can generate vivid and high-quality stylization results. Meanwhile, our AdaCM is ultrafast and can process a 4K resolution image in 6ms on one V100 GPU.

Hongchen Tan, Baocai Yin, Kun Wei et al.

We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout Refinement (ALR) module and a Layout Visual Refinement (LVR) loss. The ALR module aligns the layout structure (which refers to locations of objects and background) of a synthesized image with that of its corresponding real image. In ALR module, we proposed an Adaptive Layout Refinement (ALR) loss to balance the matching of hard and easy features, for more efficient layout structure matching. Based on the refined layout structure, the LVR loss further refines the visual representation within the layout area. Experimental results on two widely-used datasets show that ALR-GAN performs competitively at the Text-to-Image generation task.

Xin Li, Botian Shi, Yuenan Hou et al.

Multi-modal 3D object detection has been an active research topic in autonomous driving. Nevertheless, it is non-trivial to explore the cross-modal feature fusion between sparse 3D points and dense 2D pixels. Recent approaches either fuse the image features with the point cloud features that are projected onto the 2D image plane or combine the sparse point cloud with dense image pixels. These fusion approaches often suffer from severe information loss, thus causing sub-optimal performance. To address these problems, we construct the homogeneous structure between the point cloud and images to avoid projective information loss by transforming the camera features into the LiDAR 3D space. In this paper, we propose a homogeneous multi-modal feature fusion and interaction method (HMFI) for 3D object detection. Specifically, we first design an image voxel lifter module (IVLM) to lift 2D image features into the 3D space and generate homogeneous image voxel features. Then, we fuse the voxelized point cloud features with the image features from different regions by introducing the self-attention based query fusion mechanism (QFM). Next, we propose a voxel feature interaction module (VFIM) to enforce the consistency of semantic information from identical objects in the homogeneous point cloud and image voxel representations, which can provide object-level alignment guidance for cross-modal feature fusion and strengthen the discriminative ability in complex backgrounds. We conduct extensive experiments on the KITTI and Waymo Open Dataset, and the proposed HMFI achieves better performance compared with the state-of-the-art multi-modal methods. Particularly, for the 3D detection of cyclist on the KITTI benchmark, HMFI surpasses all the published algorithms by a large margin.

Xin Li, Bingchen Li, Yeying Jin et al.

Compressed Image Super-resolution (CSR) aims to simultaneously super-resolve the compressed images and tackle the challenging hybrid distortions caused by compression. However, existing works on CSR usually focuses on a single compression codec, i.e., JPEG, ignoring the diverse traditional or learning-based codecs in the practical application, e.g., HEVC, VVC, HIFIC, etc. In this work, we propose the first universal CSR framework, dubbed UCIP, with dynamic prompt learning, intending to jointly support the CSR distortions of any compression codecs/modes. Particularly, an efficient dynamic prompt strategy is proposed to mine the content/spatial-aware task-adaptive contextual information for the universal CSR task, using only a small amount of prompts with spatial size 1x1. To simplify contextual information mining, we introduce the novel MLP-like framework backbone for our UCIP by adapting the Active Token Mixer (ATM) to CSR tasks for the first time, where the global information modeling is only taken in horizontal and vertical directions with offset prediction. We also build an all-in-one benchmark dataset for the CSR task by collecting the datasets with the popular 6 diverse traditional and learning-based codecs, including JPEG, HEVC, VVC, HIFIC, etc., resulting in 23 common degradations. Extensive experiments have shown the consistent and excellent performance of our UCIP on universal CSR tasks. The project can be found in https://lixinustc.github.io/UCIP.github.io

Xiaoshuai Fan, Xin Li, Zhibo Chen

As a commonly-used image compression format, JPEG has been broadly applied in the transmission and storage of images. To further reduce the compression cost while maintaining the quality of JPEG images, lossless transcoding technology has been proposed to recompress the compressed JPEG image in the DCT domain. Previous works, on the other hand, typically reduce the redundancy of DCT coefficients and optimize the probability prediction of entropy coding in a hand-crafted manner that lacks generalization ability and flexibility. To tackle the above challenge, we propose the learned lossless JPEG transcoding framework via Joint Lossy and Residual Compression. Instead of directly optimizing the entropy estimation, we focus on the redundancy that exists in the DCT coefficients. To the best of our knowledge, we are the first to utilize the learned end-to-end lossy transform coding to reduce the redundancy of DCT coefficients in a compact representational domain. We also introduce residual compression for lossless transcoding, which adaptively learns the distribution of residual DCT coefficients before compressing them using context-based entropy coding. Our proposed transcoding architecture shows significant superiority in the compression of JPEG images thanks to the collaboration of learned lossy transform coding and residual entropy coding. Extensive experiments on multiple datasets have demonstrated that our proposed framework can achieve about 21.49% bits saving in average based on JPEG compression, which outperforms the typical lossless transcoding framework JPEG-XL by 3.51%.

Weiyue Zhao, Hao Lu, Xinyi Ye et al.

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in correspondence-specific barycentric coordinate systems (BCS) with affine invariance. To know \textit{when and where to trust} the encoded coordinates, we implement PCFs in a probabilistic network termed PCF-Net, which parameterizes the distribution of coordinate fields as Gaussian mixture models. By jointly optimizing coordinate fields and their confidence conditioned on dense flows, PCF-Net can work with various feature descriptors when quantifying the reliability of PCFs by confidence maps. An interesting observation of this work is that the learned confidence map converges to geometrically coherent and semantically consistent regions, which facilitates robust coordinate representation. By delivering the confident coordinates to keypoint/feature descriptors, we show that PCF-Net can be used as a plug-in to existing correspondence-dependent approaches. Extensive experiments on both indoor and outdoor datasets suggest that accurate geometric invariant coordinates help to achieve the state of the art in several correspondence problems, such as sparse feature matching, dense image registration, camera pose estimation, and consistency filtering. Further, the interpretable confidence map predicted by PCF-Net can also be leveraged to other novel applications from texture transfer to multi-homography classification.

Weiyue Zhao, Hao Lu, Zhiguo Cao et al.

There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information associated with repeated patterns makes coordinate representations a useful supplement to appearance representations for improving feature correspondences. However, the issue of appropriate coordinate representation has remained unresolved. In this study, we demonstrate that geometric-invariant coordinate representations, such as barycentric coordinates, can significantly reduce mismatches between features. The first step is to establish a theoretical foundation for geometrically invariant coordinates. We present a seed matching and filtering network (SMFNet) that combines feature matching and consistency filtering with a coarse-to-fine matching strategy in order to acquire reliable sparse correspondences. We then introduce DEGREE, a novel anchor-to-barycentric (A2B) coordinate encoding approach, which generates multiple affine-invariant correspondence coordinates from paired images. DEGREE can be used as a plug-in with standard descriptors, feature matchers, and consistency filters to improve the matching quality. Extensive experiments in synthesized indoor and outdoor datasets demonstrate that DEGREE alleviates the problem of repeated patterns and helps achieve state-of-the-art performance. Furthermore, DEGREE also reports competitive performance in the third Image Matching Challenge at CVPR 2021. This approach offers a new perspective to alleviate the problem of repeated patterns and emphasizes the importance of choosing coordinate representations for feature correspondences.

Qing Wu, Xin Li, Hongjiang Wei et al.

Neural Radiance Field (NeRF) has widely received attention in Sparse-View Computed Tomography (SVCT) reconstruction tasks as a self-supervised deep learning framework. NeRF-based SVCT methods represent the desired CT image as a continuous function of spatial coordinates and train a Multi-Layer Perceptron (MLP) to learn the function by minimizing loss on the SV sinogram. Benefiting from the continuous representation provided by NeRF, the high-quality CT image can be reconstructed. However, existing NeRF-based SVCT methods strictly suppose there is completely no relative motion during the CT acquisition because they require \textit{accurate} projection poses to model the X-rays that scan the SV sinogram. Therefore, these methods suffer from severe performance drops for real SVCT imaging with motion. In this work, we propose a self-calibrating neural field to recover the artifacts-free image from the rigid motion-corrupted SV sinogram without using any external data. Specifically, we parametrize the inaccurate projection poses caused by rigid motion as trainable variables and then jointly optimize these pose variables and the MLP. We conduct numerical experiments on a public CT image dataset. The results indicate our model significantly outperforms two representative NeRF-based methods for SVCT reconstruction tasks with four different levels of rigid motion.

Zhengming Yu, Zhiyang Dou, Xiaoxiao Long et al.

We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited topologies and poor geometry details. To generate high-quality surfaces of arbitrary topologies, we use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. Furthermore, we propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF and support high-resolution mesh extraction. We further show that our new pipeline significantly outperforms the prior approaches to learning the distance fields, such as the grid-based AutoEncoder, which is not scalable and incapable of learning accurate UDF. In addition, we adopt a curriculum learning strategy to efficiently embed various surfaces. With the pretrained shape latent space, we employ a latent diffusion model to acquire the distribution of various shapes. Extensive experiments are presented on using Surf-D for unconditional generation, category conditional generation, image conditional generation, and text-to-shape tasks. The experiments demonstrate the superior performance of Surf-D in shape generation across multiple modalities as conditions. Visit our project page at https://yzmblog.github.io/projects/SurfD/.

Xiaotao Zheng, Xingye Yue, Zhihong Xia et al.

Semilinear parabolic partial differential equations (PDEs) are fundamental to modeling complex dynamical systems across scientific domains. The Deep Backward Stochastic Differential Equation (BSDE) method is a promising approach for high-dimensional PDEs; however, existing convergence results apply only to globally Lipschitz generators, excluding important cases such as Allen--Cahn and Hamilton--Jacobi--Bellman (HJB) equations. This paper presents both a theoretical and a computational advance for Deep BSDE methods. Theoretically, we establish the convergence theory for non--Lipschitz generators--covering Allen--Cahn equations with cubic nonlinearity and HJB equations with quadratic gradient growth--based on a bounded double--well lemma and a truncated-BSDE analysis within the Bouchard--Touzi--Zhang theory. Computationally, we instantiate the framework with XNet, a shallow architecture with $\mathcal O(L)$ parameters that preserves strong approximation while substantially reducing optimization and computational cost. Numerical experiments on 100--dimensional PDEs corroborate the predicted convergence behavior and demonstrate significant efficiency gains over standard feedforward implementations.

Xinyi Ye, Weiyue Zhao, Tianqi Liu et al.

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods,DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

Qiuhong Shen, Xin Li, Fanyang Meng et al.

Visual object tracking acts as a pivotal component in various emerging video applications. Despite the numerous developments in visual tracking, existing deep trackers are still likely to fail when tracking against objects with dramatic variation. These deep trackers usually do not perform online update or update single sub-branch of the tracking model, for which they cannot adapt to the appearance variation of objects. Efficient updating methods are therefore crucial for tracking while previous meta-updater optimizes trackers directly over parameter space, which is prone to over-fit even collapse on longer sequences. To address these issues, we propose a context-aware tracking model to optimize the tracker over the representation space, which jointly meta-update both branches by exploiting information along the whole sequence, such that it can avoid the over-fitting problem. First, we note that the embedded features of the localization branch and the box-estimation branch, focusing on the local and global information of the target, are effective complements to each other. Based on this insight, we devise a context-aggregation module to fuse information in historical frames, followed by a context-aware module to learn affinity vectors for both branches of the tracker. Besides, we develop a dedicated meta-learning scheme, on account of fast and stable updating with limited training samples. The proposed tracking method achieves an EAO score of 0.514 on VOT2018 with the speed of 40FPS, demonstrating its capability of improving the accuracy and robustness of the underlying tracker with little speed drop.

Xin Li

Neural and immune memory rely on different biological mechanisms but face the same computational problem: future situations rarely repeat past ones exactly. Memory must retain distinctions that alter future responses while discarding irrelevant variation. We formulate this problem as \emph{scaffold-flow memory}: fast, state-dependent responses constitute the flow, whereas slowly changing physical variables form a scaffold that constrains future dynamics. Consolidation writes a predictive coarse-graining of experience into that scaffold. A useful coarse-graining must preserve future-relevant distinctions, generalize to novel experiences, support approximately autonomous coarse dynamics, and provide enough future benefit to justify its physical cost. We quantify failures of coarse autonomy through a leakage measure, relate leakage to excess future error, and identify persistent memory classes with slow dynamical modes. We further show that when experience does not self-average, storage is necessary rather than efficient. In a Willshaw associative memory, a metastable neural attractor, and a stochastic affinity-maturation model, future risk is minimized at an intermediate granularity: overly fine representations waste capacity and generalize poorly, whereas overly coarse ones merge situations requiring different responses. These results support a common computational principle: \emph{memory consolidation selects a predictive, dynamically usable, and affordable representation of the past}.

Guangqi Xie, Xin Li, Xiaohan Pan et al.

Remote medical diagnosis has emerged as a critical and indispensable technique in practical medical systems, where medical data are required to be efficiently compressed and transmitted for diagnosis by either professional doctors or intelligent diagnosis devices. In this process, a large amount of redundant content irrelevant to the diagnosis is subjected to high-fidelity coding, leading to unnecessary transmission costs. To mitigate this, we propose diagnosis-oriented medical image compression, a special semantic compression task designed for medical scenarios, targeting to reduce the compression cost without compromising the diagnosis accuracy. However, collecting sufficient medical data to optimize such a compression system is significantly expensive and challenging due to privacy issues and the lack of professional annotation. In this study, we propose DMIC, the first efficient transfer learning-based codec, for diagnosis-oriented medical image compression, which can be effectively optimized with only few-shot annotated medical examples, by reusing the knowledge in the existing reinforcement learning-based task-driven semantic coding framework, i.e., HRLVSC [1]. Concretely, we focus on tuning only the partial parameters of the policy network for bit allocation within HRLVSC, which enables it to adapt to the medical images. In this work, we validate our DMIC with the typical medical task, Coronary Artery Segmentation. Extensive experiments have demonstrated that our DMIC can achieve 47.594%BD-Rate savings compared to the HEVC anchor, by tuning only the A2C module (2.7% parameters) of the policy network with only 1 medical sample.

Lianting Hu, Huiying Liang, Jiajie Tang et al.

Background: Medical images are more difficult to acquire and annotate than natural images, which results in data augmentation technologies often being used in medical image segmentation tasks. Most data augmentation technologies used in medical segmentation were originally developed on natural images and do not take into account the characteristic that the overall layout of medical images is standard and fixed. Methods: Based on the characteristics of medical images, we developed the cutting-splicing data augmentation (CS-DA) method, a novel data augmentation technology for medical image segmentation. CS-DA augments the dataset by splicing different position components cut from different original medical images into a new image. The characteristics of the medical image result in the new image having the same layout as and similar appearance to the original image. Compared with classical data augmentation technologies, CS-DA is simpler and more robust. Moreover, CS-DA does not introduce any noise or fake information into the newly created image. Results: To explore the properties of CS-DA, many experiments are conducted on eight diverse datasets. On the training dataset with the small sample size, CS-DA can effectively increase the performance of the segmentation model. When CS-DA is used together with classical data augmentation technologies, the performance of the segmentation model can be further improved and is much better than that of CS-DA and classical data augmentation separately. We also explored the influence of the number of components, the position of the cutting line, and the splicing method on the CS-DA performance. Conclusions: The excellent performance of CS-DA in the experiment has confirmed the effectiveness of CS-DA, and provides a new data augmentation idea for the small sample segmentation task.

Siyu Cao, Hangting Chen, Peng Chen et al.

We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of HunyuanImage 3.0 relies on several key components, including meticulous data curation, advanced architecture design, a native Chain-of-Thoughts schema, progressive model pre-training, aggressive model post-training, and an efficient infrastructure that enables large-scale training and inference. With these advancements, we successfully trained a Mixture-of-Experts (MoE) model comprising over 80 billion parameters in total, with 13 billion parameters activated per token during inference, making it the largest and most powerful open-source image generative model to date. We conducted extensive experiments and the results of automatic and human evaluation of text-image alignment and visual quality demonstrate that HunyuanImage 3.0 rivals previous state-of-the-art models. By releasing the code and weights of HunyuanImage 3.0, we aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant multimodal ecosystem. All open source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanImage-3.0

Xuanzhao Dong, Wenhui Zhu, Xiwen Chen et al.

Autoregressive models (ARMs) have long dominated the landscape of biomedical vision-language models (VLMs). Recently, masked diffusion models such as LLaDA have emerged as promising alternatives, yet their application in the biomedical domain remains largely underexplored. To bridge this gap, we introduce \textbf{LLaDA-MedV}, the first large language diffusion model tailored for biomedical image understanding through vision instruction tuning. LLaDA-MedV achieves relative performance gains of 7.855\% over LLaVA-Med and 1.867\% over LLaDA-V in the open-ended biomedical visual conversation task, and sets new state-of-the-art accuracy on the closed-form subset of three VQA benchmarks: 84.93\% on VQA-RAD, 92.31\% on SLAKE, and 95.15\% on PathVQA. Furthermore, a detailed comparison with LLaVA-Med suggests that LLaDA-MedV is capable of generating reasonably longer responses by explicitly controlling response length, which can lead to more informative outputs. We also conduct an in-depth analysis of both the training and inference stages, highlighting the critical roles of initialization weight selection, fine-tuning strategies, and the interplay between sampling steps and response repetition. The code and model weight is released at https://github.com/LLM-VLM-GSL/LLaDA-MedV.

Jionghao Wang, Cheng Lin, Yuan Liu et al.

Point-based representations have consistently played a vital role in geometric data structures. Most point cloud learning and processing methods typically leverage the unordered and unconstrained nature to represent the underlying geometry of 3D shapes. However, how to extract meaningful structural information from unstructured point cloud distributions and transform them into semantically meaningful point distributions remains an under-explored problem. We present PDT, a novel framework for point distribution transformation with diffusion models. Given a set of input points, PDT learns to transform the point set from its original geometric distribution into a target distribution that is semantically meaningful. Our method utilizes diffusion models with novel architecture and learning strategy, which effectively correlates the source and the target distribution through a denoising process. Through extensive experiments, we show that our method successfully transforms input point clouds into various forms of structured outputs - ranging from surface-aligned keypoints, and inner sparse joints to continuous feature lines. The results showcase our framework's ability to capture both geometric and semantic features, offering a powerful tool for various 3D geometry processing tasks where structured point distributions are desired. Code will be available at this link: https://github.com/shanemankiw/PDT.

Yixin Gao, Xin Li, Xiaohan Pan et al.

We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors. Unlike most existing works that need to design and optimize image codecs from scratch, our UniMIC introduces the visual codec repository, which incorporates amounts of representative image codecs and directly uses them as the basic codecs for various practical applications. Moreover, we propose multi-grained textual coding, where variable-length content prompt and compression prompt are designed and encoded to assist the perceptual reconstruction through the multi-modality conditional generation. In particular, a universal perception compensator is proposed to improve the perception quality of decoded images from all basic codecs at the decoder side by reusing text-assisted diffusion priors from stable diffusion. With the cooperation of the above three strategies, our UniMIC achieves a significant improvement of RDP optimization for different compression codecs, e.g., traditional and learnable codecs, and different compression costs, e.g., ultra-low bitrates. The code will be available in https://github.com/Amygyx/UniMIC .

Yongqing Liang, Huijun Han, Xin Li

Solving point-wise feature correspondence in visual data is a fundamental problem in computer vision. A powerful model that addresses this challenge is to formulate it as graph matching, which entails solving a Quadratic Assignment Problem (QAP) with node-wise and edge-wise constraints. However, solving such a QAP can be both expensive and difficult due to numerous local extreme points. In this work, we introduce a novel linear model and solver designed to accelerate the computation of graph matching. Specifically, we employ a positive semi-definite matrix approximation to establish the structural attribute constraint.We then transform the original QAP into a linear model that is concave for maximization. This model can subsequently be solved using the Sinkhorn optimal transport algorithm, known for its enhanced efficiency and numerical stability compared to existing approaches. Experimental results on the widely used benchmark PascalVOC showcase that our algorithm achieves state-of-the-art performance with significantly improved efficiency. Source code: https://github.com/xmlyqing00/clap

Cheng Yan, Xin Li, Guoqiang Li

To date, machine learning for human action recognition in video has been widely implemented in sports activities. Although some studies have been successful in the past, precision is still the most significant concern. In this study, we present a high-accuracy framework to automatically clip the sports video stream by using a three-level prediction algorithm based on two classical open-source structures, i.e., YOLO-v3 and OpenPose. It is found that by using a modest amount of sports video training data, our methodology can perform sports activity highlights clipping accurately. Comparing with the previous systems, our methodology shows some advantages in accuracy. This study may serve as a new clipping system to extend the potential applications of the video summarization in sports field, as well as facilitates the development of match analysis system.

Xin Li, Chengyin Li, Dongxiao Zhu

During the COVID-19 pandemic, there has been an emerging need for rapid, dedicated, and point-of-care COVID-19 patient disposition techniques to optimize resource utilization and clinical workflow. In view of this need, we present COVID-MobileXpert: a lightweight deep neural network (DNN) based mobile app that can use chest X-ray (CXR) for COVID-19 case screening and radiological trajectory prediction. We design and implement a novel three-player knowledge transfer and distillation (KTD) framework including a pre-trained attending physician (AP) network that extracts CXR imaging features from a large scale of lung disease CXR images, a fine-tuned resident fellow (RF) network that learns the essential CXR imaging features to discriminate COVID-19 from pneumonia and/or normal cases with a small amount of COVID-19 cases, and a trained lightweight medical student (MS) network to perform on-device COVID-19 patient triage and follow-up. To tackle the challenge of vastly similar and dominant fore- and background in medical images, we employ novel loss functions and training schemes for the MS network to learn the robust features. We demonstrate the significant potential of COVID-MobileXpert for rapid deployment via extensive experiments with diverse MS architecture and tuning parameter settings. The source codes for cloud and mobile based models are available from the following url: https://github.com/xinli0928/COVID-Xray.

Jionghao Wang, Yuan Liu, Zhiyang Dou et al.

In this paper, we introduce a novel text-to-avatar generation method that separately generates the human body and the clothes and allows high-quality animation on the generated avatar. While recent advancements in text-to-avatar generation have yielded diverse human avatars from text prompts, these methods typically combine all elements-clothes, hair, and body-into a single 3D representation. Such an entangled approach poses challenges for downstream tasks like editing or animation. To overcome these limitations, we propose a novel disentangled 3D avatar representation named Sequentially Offset-SMPL (SO-SMPL), building upon the SMPL model. SO-SMPL represents the human body and clothes with two separate meshes but associates them with offsets to ensure the physical alignment between the body and the clothes. Then, we design a Score Distillation Sampling (SDS)-based distillation framework to generate the proposed SO-SMPL representation from text prompts. Our approach not only achieves higher texture and geometry quality and better semantic alignment with text prompts, but also significantly improves the visual quality of character animation, virtual try-on, and avatar editing. Project page: https://shanemankiw.github.io/SO-SMPL/.

Hanxin Zhu, Tianyu He, Xin Li et al. · microsoft-research

Neural Radiance Field (NeRF) has achieved superior performance for novel view synthesis by modeling the scene with a Multi-Layer Perception (MLP) and a volume rendering procedure, however, when fewer known views are given (i.e., few-shot view synthesis), the model is prone to overfit the given views. To handle this issue, previous efforts have been made towards leveraging learned priors or introducing additional regularizations. In contrast, in this paper, we for the first time provide an orthogonal method from the perspective of network structure. Given the observation that trivially reducing the number of model parameters alleviates the overfitting issue, but at the cost of missing details, we propose the multi-input MLP (mi-MLP) that incorporates the inputs (i.e., location and viewing direction) of the vanilla MLP into each layer to prevent the overfitting issue without harming detailed synthesis. To further reduce the artifacts, we propose to model colors and volume density separately and present two regularization terms. Extensive experiments on multiple datasets demonstrate that: 1) although the proposed mi-MLP is easy to implement, it is surprisingly effective as it boosts the PSNR of the baseline from $14.73$ to $24.23$. 2) the overall framework achieves state-of-the-art results on a wide range of benchmarks. We will release the code upon publication.

Elham Ravanbakhsh, Yongqing Liang, J. Ramanujam et al.

This paper provides a review on representation learning for videos. We classify recent spatiotemporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective features for videos is a fundamental problem in computer vision tasks involving video analysis and understanding. Existing features can be generally categorized into spatial and temporal features. Their effectiveness under variations of illumination, occlusion, view and background are discussed. Finally, we discuss the remaining challenges in existing deep video representation learning studies.

Deshui Miao, Xin Li, Zhenyu He et al.

Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel processing simultaneously, thereby constraining the learning of dynamic, target-aware features. To tackle these limitations, this paper proposes a spatial-temporal multi-level association framework, which jointly associates reference frame, test frame, and object features to achieve sufficient interaction and parallel target ID association with a spatial-temporal memory bank for efficient video object segmentation. Specifically, we construct a spatial-temporal multi-level feature association module to learn better target-aware features, which formulates feature extraction and interaction as the efficient operations of object self-attention, reference object enhancement, and test reference correlation. In addition, we propose a spatial-temporal memory to assist feature association and temporal ID assignment and correlation. We evaluate the proposed method by conducting extensive experiments on numerous video object segmentation datasets, including DAVIS 2016/2017 val, DAVIS 2017 test-dev, and YouTube-VOS 2018/2019 val. The favorable performance against the state-of-the-art methods demonstrates the effectiveness of our approach. All source code and trained models will be made publicly available.

Stepan Tretiakov, Xingjian Li, Krishna Kumar

Neural operators, particularly the Deep Operator Network (DeepONet), have shown promise in learning mappings between function spaces for solving differential equations. However, standard DeepONet requires input functions to be sampled at fixed locations, limiting its applicability when sensor configurations vary or inputs exist on irregular grids. We introduce the Set Operator Network (SetONet), which modifies DeepONet's branch network to process input functions as unordered sets of location-value pairs. By incorporating Deep Sets principles, SetONet ensures permutation invariance while maintaining the same parameter count as the baseline. On classical operator-learning benchmarks, SetONet achieves parity with DeepONet on fixed layouts while sustaining accuracy under variable sensor configurations or sensor drop-off - conditions for which standard DeepONet is not applicable. More significantly, SetONet natively handles problems where inputs are naturally represented as unstructured point clouds (such as point sources or density samples) rather than values on fixed grids, a capability standard DeepONet lacks. On heat conduction with point sources, advection-diffusion modeling chemical plumes, and optimal transport between density samples, SetONet learns operators end-to-end without rasterization or multi-stage pipelines. These problems feature inputs that are naturally discrete point sets (point sources or density samples) rather than functions on fixed grids. SetONet is a DeepONet-class architecture that addresses such problems with a lightweight design, significantly broadening the applicability of operator learning to problems with variable, incomplete, or unstructured input data.

Xi Tong, Xing Luo, Jiangxin Yang et al.

Multispectral imaging plays a critical role in a range of intelligent transportation applications, including advanced driver assistance systems (ADAS), traffic monitoring, and night vision. However, accurate visible and thermal (RGB-T) image registration poses a significant challenge due to the considerable modality differences. In this paper, we present a novel joint Self-Correlation and Cross-Correspondence Estimation Framework (SC3EF), leveraging both local representative features and global contextual cues to effectively generate RGB-T correspondences. For this purpose, we design a convolution-transformer-based pipeline to extract local representative features and encode global correlations of intra-modality for inter-modality correspondence estimation between unaligned visible and thermal images. After merging the local and global correspondence estimation results, we further employ a hierarchical optical flow estimation decoder to progressively refine the estimated dense correspondence maps. Extensive experiments demonstrate the effectiveness of our proposed method, outperforming the current state-of-the-art (SOTA) methods on representative RGB-T datasets. Furthermore, it also shows competitive generalization capabilities across challenging scenarios, including large parallax, severe occlusions, adverse weather, and other cross-modal datasets (e.g., RGB-N and RGB-D).

Raghav Pant, Sikan Li, Xingjian Li et al.

There is increasing interest in solving partial differential equations (PDEs) by casting them as machine learning problems. Recently, there has been a spike in exploring Kolmogorov-Arnold Networks (KANs) as an alternative to traditional neural networks represented by Multi-Layer Perceptrons (MLPs). While showing promise, their performance advantages in physics-based problems remain largely unexplored. Several critical questions persist: Can KANs capture complex physical dynamics and under what conditions might they outperform traditional architectures? In this work, we present a comparative study of KANs and MLPs for learning physical systems governed by PDEs. We assess their performance when applied in deep operator networks (DeepONet) and graph network-based simulators (GNS), and test them on physical problems that vary significantly in scale and complexity. Drawing inspiration from the Kolmogorov Representation Theorem, we examine the behavior of KANs and MLPs across shallow and deep network architectures. Our results reveal that although KANs do not consistently outperform MLPs when configured as deep neural networks, they demonstrate superior expressiveness in shallow network settings, significantly outpacing MLPs in accuracy over our test cases. This suggests that KANs are a promising choice, offering a balance of efficiency and accuracy in applications involving physical systems.

Jingdong Zhang, Hanrong Ye, Xin Li et al.

In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting adversarial training for extra regularization, which achieve promising performance improvements, while still suffering from the lack of direct pixel-wise supervision and extra training of heavy mapping networks. To effectively tackle this challenge, we propose a novel approach to optimize a set of compact learnable hierarchical task tokens, including global and fine-grained ones, to discover consistent pixel-wise supervision signals in both feature and prediction levels. Specifically, the global task tokens are designed for effective cross-task feature interactions in a global context. Then, a group of fine-grained task-specific spatial tokens for each task is learned from the corresponding global task tokens. It is embedded to have dense interactions with each task-specific feature map. The learned global and local fine-grained task tokens are further used to discover pseudo task-specific dense labels at different levels of granularity, and they can be utilized to directly supervise the learning of the multi-task dense prediction framework. Extensive experimental results on challenging NYUD-v2, Cityscapes, and PASCAL Context datasets demonstrate significant improvements over existing state-of-the-art methods for partially annotated multi-task dense prediction.

Elham Ravanbakhsh, Cheng Niu, Yongqing Liang et al.

Semantic segmentation is a core computer vision problem, but the high costs of data annotation have hindered its wide application. Weakly-Supervised Semantic Segmentation (WSSS) offers a cost-efficient workaround to extensive labeling in comparison to fully-supervised methods by using partial or incomplete labels. Existing WSSS methods have difficulties in learning the boundaries of objects leading to poor segmentation results. We propose a novel and effective framework that addresses these issues by leveraging visual foundation models inside the bounding box. Adopting a two-stage WSSS framework, our proposed network consists of a pseudo-label generation module and a segmentation module. The first stage leverages Segment Anything Model (SAM) to generate high-quality pseudo-labels. To alleviate the problem of delineating precise boundaries, we adopt SAM inside the bounding box with the help of another pre-trained foundation model (e.g., Grounding-DINO). Furthermore, we eliminate the necessity of using the supervision of image labels, by employing CLIP in classification. Then in the second stage, the generated high-quality pseudo-labels are used to train an off-the-shelf segmenter that achieves the state-of-the-art performance on PASCAL VOC 2012 and MS COCO 2014.

Xin Li, Peng Li, Zeyong Wei et al.

Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different modalities. In this paper, we address these challenges by exploring the implicit semantic and geometric correlations between 2D and 3D data of the same objects/scenes. We propose a new cross-modal BERT-style self-supervised learning paradigm, called Cross-BERT. To facilitate pretraining for irregular and sparse point clouds, we design two self-supervised tasks to boost cross-modal interaction. The first task, referred to as Point-Image Alignment, aims to align features between unimodal and cross-modal representations to capture the correspondences between the 2D and 3D modalities. The second task, termed Masked Cross-modal Modeling, further improves mask modeling of BERT by incorporating high-dimensional semantic information obtained by cross-modal interaction. By performing cross-modal interaction, Cross-BERT can smoothly reconstruct the masked tokens during pretraining, leading to notable performance enhancements for downstream tasks. Through empirical evaluation, we demonstrate that Cross-BERT outperforms existing state-of-the-art methods in 3D downstream applications. Our work highlights the effectiveness of leveraging cross-modal 2D knowledge to strengthen 3D point cloud representation and the transferable capability of BERT across modalities.

Hao Fang, Zechao Zhan, Weixin Feng et al.

Recent advances in image generation and editing technologies have enabled state-of-the-art models to achieve impressive results in general domains. However, when applied to e-commerce scenarios, these general models often encounter consistency limitations. To address this challenge, we introduce TBStar-Edit, an new image editing model tailored for the e-commerce domain. Through rigorous data engineering, model architecture design and training strategy, TBStar-Edit achieves precise and high-fidelity image editing while maintaining the integrity of product appearance and layout. Specifically, for data engineering, we establish a comprehensive data construction pipeline, encompassing data collection, construction, filtering, and augmentation, to acquire high-quality, instruction-following, and strongly consistent editing data to support model training. For model architecture design, we design a hierarchical model framework consisting of a base model, pattern shifting modules, and consistency enhancement modules. For model training, we adopt a two-stage training strategy to enhance the consistency preservation: first stage for editing pattern shifting, and second stage for consistency enhancement. Each stage involves training different modules with separate datasets. Finally, we conduct extensive evaluations of TBStar-Edit on a self-proposed e-commerce benchmark, and the results demonstrate that TBStar-Edit outperforms existing general-domain editing models in both objective metrics (VIE Score) and subjective user preference.