Jiaqi Yang

Qiao Wu, Jiaqi Yang, Kun Sun et al.

3D single object tracking (SOT) is an indispensable part of automated driving. Existing approaches rely heavily on large, densely labeled datasets. However, annotating point clouds is both costly and time-consuming. Inspired by the great success of cycle tracking in unsupervised 2D SOT, we introduce the first semi-supervised approach to 3D SOT. Specifically, we introduce two cycle-consistency strategies for supervision: 1) Self tracking cycles, which leverage labels to help the model converge better in the early stages of training; 2) forward-backward cycles, which strengthen the tracker's robustness to motion variations and the template noise caused by the template update strategy. Furthermore, we propose a data augmentation strategy named SOTMixup to improve the tracker's robustness to point cloud diversity. SOTMixup generates training samples by sampling points in two point clouds with a mixing rate and assigns a reasonable loss weight for training according to the mixing rate. The resulting MixCycle approach generalizes to appearance matching-based trackers. On the KITTI benchmark, based on the P2B tracker, MixCycle trained with $\textbf{10\%}$ labels outperforms P2B trained with $\textbf{100\%}$ labels, and achieves a $\textbf{28.4\%}$ precision improvement when using $\textbf{1\%}$ labels. Our code will be released at \url{https://github.com/Mumuqiao/MixCycle}.

Ling Gao, Yuxuan Liang, Jiaqi Yang et al. · tsinghua

Event cameras have recently gained in popularity as they hold strong potential to complement regular cameras in situations of high dynamics or challenging illumination. An important problem that may benefit from the addition of an event camera is given by Simultaneous Localization And Mapping (SLAM). However, in order to ensure progress on event-inclusive multi-sensor SLAM, novel benchmark sequences are needed. Our contribution is the first complete set of benchmark datasets captured with a multi-sensor setup containing an event-based stereo camera, a regular stereo camera, multiple depth sensors, and an inertial measurement unit. The setup is fully hardware-synchronized and underwent accurate extrinsic calibration. All sequences come with ground truth data captured by highly accurate external reference devices such as a motion capture system. Individual sequences include both small and large-scale environments, and cover the specific challenges targeted by dynamic vision sensors.

Jiaben Chen, Renrui Zhang, Dongze Lian et al. · tsinghua

Current audio-visual separation methods share a standard architecture design where an audio encoder-decoder network is fused with visual encoding features at the encoder bottleneck. This design confounds the learning of multi-modal feature encoding with robust sound decoding for audio separation. To generalize to a new instrument: one must finetune the entire visual and audio network for all musical instruments. We re-formulate visual-sound separation task and propose Instrument as Query (iQuery) with a flexible query expansion mechanism. Our approach ensures cross-modal consistency and cross-instrument disentanglement. We utilize "visually named" queries to initiate the learning of audio queries and use cross-modal attention to remove potential sound source interference at the estimated waveforms. To generalize to a new instrument or event class, drawing inspiration from the text-prompt design, we insert an additional query as an audio prompt while freezing the attention mechanism. Experimental results on three benchmarks demonstrate that our iQuery improves audio-visual sound source separation performance.

Team Seedance, De Chen, Liyang Chen et al. · gatech

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

Jiaqi Yang, Qi Lei, Jason D. Lee et al. · tsinghua

We give novel algorithms for multi-task and lifelong linear bandits with shared representation. Specifically, we consider the setting where we play $M$ linear bandits with dimension $d$, each for $T$ rounds, and these $M$ bandit tasks share a common $k(\ll d)$ dimensional linear representation. For both the multi-task setting where we play the tasks concurrently, and the lifelong setting where we play tasks sequentially, we come up with novel algorithms that achieve $\widetilde{O}\left(d\sqrt{kMT} + kM\sqrt{T}\right)$ regret bounds, which matches the known minimax regret lower bound up to logarithmic factors and closes the gap in existing results [Yang et al., 2021]. Our main technique include a more efficient estimator for the low-rank linear feature extractor and an accompanied novel analysis for this estimator.

Jiaben Chen, Yichen Zhu, Dongze Lian et al. · tsinghua

Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining both synthesis-based and warping networks. However, few of those methods fully respect the intrinsic characteristics of events streams. Given that event cameras only encode intensity changes and polarity rather than color intensities, estimating optical flow from events is arguably more difficult than from RGB information. We therefore propose to incorporate RGB information in an event-guided optical flow refinement strategy. Moreover, in light of the quasi-continuous nature of the time signals provided by event cameras, we propose a divide-and-conquer strategy in which event-based intermediate frame synthesis happens incrementally in multiple simplified stages rather than in a single, long stage. Extensive experiments on both synthetic and real-world datasets show that these modifications lead to more reliable and realistic intermediate frame results than previous video frame interpolation methods. Our findings underline that a careful consideration of event characteristics such as high temporal density and elevated noise benefits interpolation accuracy.

Chao Yu, Jiaxuan Gao, Weilin Liu et al. · tsinghua

There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play (SP) to build a policy pool and then train the final adaptive policy against this pool. A crucial limitation of this framework is that every policy in the pool is optimized w.r.t. the environment reward function, which implicitly assumes that the testing partners of the adaptive policy will be precisely optimizing the same reward function as well. However, human objectives are often substantially biased according to their own preferences, which can differ greatly from the environment reward. We propose a more general framework, Hidden-Utility Self-Play (HSP), which explicitly models human biases as hidden reward functions in the self-play objective. By approximating the reward space as linear functions, HSP adopts an effective technique to generate an augmented policy pool with biased policies. We evaluate HSP on the Overcooked benchmark. Empirical results show that our HSP method produces higher rewards than baselines when cooperating with learned human models, manually scripted policies, and real humans. The HSP policy is also rated as the most assistive policy based on human feedback.

Wei Fu, Chao Yu, Zelai Xu et al. · tsinghua

Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorithm of this fashion decomposes a centralized Q-function into local Q-networks with parameters shared across agents. Such an algorithmic paradigm enables centralized training and decentralized execution (CTDE) and leads to efficient learning in practice. Despite all the advantages, we revisit these two principles and show that in certain scenarios, e.g., environments with a highly multi-modal reward landscape, value decomposition, and parameter sharing can be problematic and lead to undesired outcomes. In contrast, policy gradient (PG) methods with individual policies provably converge to an optimal solution in these cases, which partially supports some recent empirical observations that PG can be effective in many MARL testbeds. Inspired by our theoretical analysis, we present practical suggestions on implementing multi-agent PG algorithms for either high rewards or diverse emergent behaviors and empirically validate our findings on a variety of domains, ranging from the simplified matrix and grid-world games to complex benchmarks such as StarCraft Multi-Agent Challenge and Google Research Football. We hope our insights could benefit the community towards developing more general and more powerful MARL algorithms. Check our project website at https://sites.google.com/view/revisiting-marl.

Yunfei Li, Tian Gao, Jiaqi Yang et al. · bytedance, tsinghua

It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic approach by alternating online RL and offline SL for tackling sparse-reward goal-conditioned problems. In the online phase, we perform RL training and collect rollout data while in the offline phase, we perform SL on those successful trajectories from the dataset. To further improve sample efficiency, we adopt additional techniques in the online phase including task reduction to generate more feasible trajectories and a value-difference-based intrinsic reward to alleviate the sparse-reward issue. We call this overall algorithm, PhAsic self-Imitative Reduction (PAIR). PAIR substantially outperforms both non-phasic RL and phasic SL baselines on sparse-reward goal-conditioned robotic control problems, including a challenging stacking task. PAIR is the first RL method that learns to stack 6 cubes with only 0/1 success rewards from scratch.

Haocheng Yuan, Chen Zhao, Shichao Fan et al.

Semantic 3D keypoints are category-level semantic consistent points on 3D objects. Detecting 3D semantic keypoints is a foundation for a number of 3D vision tasks but remains challenging, due to the ambiguity of semantic information, especially when the objects are represented by unordered 3D point clouds. Existing unsupervised methods tend to generate category-level keypoints in implicit manners, making it difficult to extract high-level information, such as semantic labels and topology. From a novel mutual reconstruction perspective, we present an unsupervised method to generate consistent semantic keypoints from point clouds explicitly. To achieve this, the proposed model predicts keypoints that not only reconstruct the object itself but also reconstruct other instances in the same category. To the best of our knowledge, the proposed method is the first to mine 3D semantic consistent keypoints from a mutual reconstruction view. Experiments under various evaluation metrics as well as comparisons with the state-of-the-arts demonstrate the efficacy of our new solution to mining semantic consistent keypoints with mutual reconstruction.

Chunlin Ren, Qingshan Xu, Shikun Zhang et al. · tsinghua

As a fundamental problem in computer vision, multi-view stereo (MVS) aims at recovering the 3D geometry of a target from a set of 2D images. Recent advances in MVS have shown that it is important to perceive non-local structured information for recovering geometry in low-textured areas. In this work, we propose a Hierarchical Prior Mining for Non-local Multi-View Stereo (HPM-MVS). The key characteristics are the following techniques that exploit non-local information to assist MVS: 1) A Non-local Extensible Sampling Pattern (NESP), which is able to adaptively change the size of sampled areas without becoming snared in locally optimal solutions. 2) A new approach to leverage non-local reliable points and construct a planar prior model based on K-Nearest Neighbor (KNN), to obtain potential hypotheses for the regions where prior construction is challenging. 3) A Hierarchical Prior Mining (HPM) framework, which is used to mine extensive non-local prior information at different scales to assist 3D model recovery, this strategy can achieve a considerable balance between the reconstruction of details and low-textured areas. Experimental results on the ETH3D and Tanks \& Temples have verified the superior performance and strong generalization capability of our method. Our code will be released.

Yuantai Zhang, Jiaqi Yang, Huajian Zeng et al.

Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for subsequent state estimation. Despite steady progress, most existing methods heavily rely on visual feature correspondences and require 3-4 seconds of sensory data for successful initialization, which limits their applicability and efficiency. With the advent of feed-forward 3D models that can directly predict point clouds from images, we revisit the visual-inertial initialization problem from a concise perspective. In this work, we propose a feature-free initialization framework that leverages up-to-scale point clouds predicted by a feed-forward 3D model, thereby obviating the need for visual feature tracking and estimation. This design substantially reduces system complexity and improves the reliability of initialization. Experiments on public datasets demonstrate that the proposed feature-free initialization method achieves the highest success rate, exceeding 90%, and significantly reduces the data duration required for successful initialization, typically to under 1.2 s. We further validate our method on a self-collected dataset covering various indoor and outdoor scenarios, demonstrating robust performance, particularly in visually degraded environments where existing methods often fail. The code and dataset are available at https://github.com/Yuantai-Z/FF-VIO-Init.

Jiaqi Yang, Bo Du, Liangpei Zhang

Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation. Therefore, a natural idea is to combine multimodal images for refined and accurate land-cover interpretation. Although many efforts have been attempted to achieve multi-source remote sensing image classification, there are still three issues as follows: 1) indiscriminate feature representation without sufficiently considering modal heterogeneity, 2) abundant features and complex computations associated with modeling long-range dependencies, and 3) overfitting phenomenon caused by sparsely labeled samples. To overcome the above barriers, a transformer-based heterogeneously salient graph representation (THSGR) approach is proposed in this paper. First, a multimodal heterogeneous graph encoder is presented to encode distinctively non-Euclidean structural features from heterogeneous data. Then, a self-attention-free multi-convolutional modulator is designed for effective and efficient long-term dependency modeling. Finally, a mean forward is put forward in order to avoid overfitting. Based on the above structures, the proposed model is able to break through modal gaps to obtain differentiated graph representation with competitive time cost, even for a small fraction of training samples. Experiments and analyses on three benchmark datasets with various state-of-the-art (SOTA) methods show the performance of the proposed approach.

Zhaoshuai Qi, Xiaojun Liu, Xiaolin Liu et al.

As the gold standard for phase retrieval, phase-shifting algorithm (PS) has been widely used in optical interferometry, fringe projection profilometry, etc. However, capturing multiple fringe patterns in PS limits the algorithm to only a narrow range of application. To this end, a deep learning (DL) model based digital PS algorithm from only a single fringe image is proposed. By training on a simulated dataset of PS fringe patterns, the learnt model, denoted PSNet, can predict fringe patterns with other PS steps when given a pattern with the first PS step. Simulation and experiment results demonstrate the PSNet's promising performance on accurate prediction of digital PS patterns, and robustness to complex scenarios such as surfaces with varying curvature and reflectance.

Jianwen Jiang, Chao Liang, Jiaqi Yang et al.

With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to the limited control of audio signals in driving human motion, existing methods often add auxiliary spatial signals to stabilize movements, which may compromise the naturalness and freedom of motion. In this paper, we propose an end-to-end audio-only conditioned video diffusion model named Loopy. Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information from the data to learn natural motion patterns and improving audio-portrait movement correlation. This method removes the need for manually specified spatial motion templates used in existing methods to constrain motion during inference. Extensive experiments show that Loopy outperforms recent audio-driven portrait diffusion models, delivering more lifelike and high-quality results across various scenarios.

Jiaqi Yang, Yucong Chen, Xiangting Meng et al.

Recently there has been a growing interest in category-level object pose and size estimation, and prevailing methods commonly rely on single view RGB-D images. However, one disadvantage of such methods is that they require accurate depth maps which cannot be produced by consumer-grade sensors. Furthermore, many practical real-world situations involve a moving camera that continuously observes its surroundings, and the temporal information of the input video streams is simply overlooked by single-view methods. We propose a novel solution that makes use of RGB video streams. Our framework consists of three modules: a scale-aware monocular dense SLAM solution, a lightweight object pose predictor, and an object-level pose graph optimizer. The SLAM module utilizes a video stream and additional scale-sensitive readings to estimate camera poses and metric depth. The object pose predictor then generates canonical object representations from RGB images. The object pose is estimated through geometric registration of these canonical object representations with estimated object depth points. All per-view estimates finally undergo optimization within a pose graph, culminating in the output of robust and accurate canonical object poses. Our experimental results demonstrate that when utilizing public dataset sequences with high-quality depth information, the proposed method exhibits comparable performance to state-of-the-art RGB-D methods. We also collect and evaluate on new datasets containing depth maps of varying quality to further quantitatively benchmark the proposed method alongside previous RGB-D based methods. We demonstrate a significant advantage in scenarios where depth input is absent or the quality of depth sensing is limited.

Tao Liu, Runze Yuan, Yi'ang Ju et al.

Reliable self-localization is a foundational skill for many intelligent mobile platforms. This paper explores the use of event cameras for motion tracking thereby providing a solution with inherent robustness under difficult dynamics and illumination. In order to circumvent the challenge of event camera-based mapping, the solution is framed in a cross-modal way. It tracks a map representation that comes directly from frame-based cameras. Specifically, the proposed method operates on top of gaussian splatting, a state-of-the-art representation that permits highly efficient and realistic novel view synthesis. The key of our approach consists of a novel pose parametrization that uses a reference pose plus first order dynamics for local differential image rendering. The latter is then compared against images of integrated events in a staggered coarse-to-fine optimization scheme. As demonstrated by our results, the realistic view rendering ability of gaussian splatting leads to stable and accurate tracking across a variety of both publicly available and newly recorded data sequences.

Pei An, Junfeng Ding, Jiaqi Yang et al.

Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences. The drastic modality gap between images and point clouds makes it challenging to learn features that are both discriminative and generalizable, leading to severe performance drops in unseen scenarios. We address this challenge by introducing a heterogeneous graph that enables refining both cross-modal features and correspondences within a unified architecture. The proposed graph represents a mapping between segmented 2D and 3D regions, which enhances cross-modal feature interaction and thus improves feature discriminability. In addition, modeling the consistency among vertices and edges within the graph enables pruning of unreliable correspondences. Building on these insights, we propose a heterogeneous graph embedded I2P registration method, termed Hg-I2P. It learns a heterogeneous graph by mining multi-path feature relationships, adapts features under the guidance of heterogeneous edges, and prunes correspondences using graph-based projection consistency. Experiments on six indoor and outdoor benchmarks under cross-domain setups demonstrate that Hg-I2P significantly outperforms existing methods in both generalization and accuracy. Code is released on https://github.com/anpei96/hg-i2p-demo.

Xinyue Zhang, Jiaqi Yang, Xiangting Meng et al.

In the realm of computer vision, the perception and reconstruction of the 3D world through vision signals heavily rely on camera intrinsic parameters, which have long been a subject of intense research within the community. In practical applications, without a strong scene geometry prior like the Manhattan World assumption or special artificial calibration patterns, monocular focal length estimation becomes a challenging task. In this paper, we propose a method for monocular focal length estimation using category-level object priors. Based on two well-studied existing tasks: monocular depth estimation and category-level object canonical representation learning, our focal solver takes depth priors and object shape priors from images containing objects and estimates the focal length from triplets of correspondences in closed form. Our experiments on simulated and real world data demonstrate that the proposed method outperforms the current state-of-the-art, offering a promising solution to the long-standing monocular focal length estimation problem.

Gaojie Lin, Jianwen Jiang, Chao Liang et al.

Diffusion-based video generation technology has advanced significantly, catalyzing a proliferation of research in human animation. However, the majority of these studies are confined to same-modality driving settings, with cross-modality human body animation remaining relatively underexplored. In this paper, we introduce, an end-to-end audio-driven human animation framework that ensures hand integrity, identity consistency, and natural motion. The key design of CyberHost is the Region Codebook Attention mechanism, which improves the generation quality of facial and hand animations by integrating fine-grained local features with learned motion pattern priors. Furthermore, we have developed a suite of human-prior-guided training strategies, including body movement map, hand clarity score, pose-aligned reference feature, and local enhancement supervision, to improve synthesis results. To our knowledge, CyberHost is the first end-to-end audio-driven human diffusion model capable of facilitating zero-shot video generation within the scope of human body. Extensive experiments demonstrate that CyberHost surpasses previous works in both quantitative and qualitative aspects.

Qiao Wu, Kun Sun, Pei An et al.

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frames are smooth, failing to cope with high temporal variation data. In this paper, we present a novel framework for 3D SOT in point clouds with high temporal variation, called HVTrack. HVTrack proposes three novel components to tackle the challenges in the high temporal variation scenario: 1) A Relative-Pose-Aware Memory module to handle temporal point cloud shape variations; 2) a Base-Expansion Feature Cross-Attention module to deal with similar object distractions in expanded search areas; 3) a Contextual Point Guided Self-Attention module for suppressing heavy background noise. We construct a dataset with high temporal variation (KITTI-HV) by setting different frame intervals for sampling in the KITTI dataset. On the KITTI-HV with 5 frame intervals, our HVTrack surpasses the state-of-the-art tracker CXTracker by 11.3%/15.7% in Success/Precision.

Huajian Zeng, Lingyun Chen, Jiaqi Yang et al.

Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that captures this structure would make manipulation behaviors easier to validate and transfer across robots. We propose FlowHOI, a two-stage flow-matching framework that generates semantically grounded, temporally coherent HOI sequences, comprising hand poses, object poses, and hand-object contact states, conditioned on an egocentric observation, a language instruction, and a 3D Gaussian splatting (3DGS) scene reconstruction. We decouple geometry-centric grasping from semantics-centric manipulation, conditioning the latter on compact 3D scene tokens and employing a motion-text alignment loss to semantically ground the generated interactions in both the physical scene layout and the language instruction. To address the scarcity of high-fidelity HOI supervision, we introduce a reconstruction pipeline that recovers aligned hand-object trajectories and meshes from large-scale egocentric videos, yielding an HOI prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI representations to real-robot execution pipelines.

Jiaxin Liu, Min Li, Wanting Xu et al.

Accurate state estimation for flexible robotic systems poses significant challenges, particularly for platforms with dynamically deforming structures that invalidate rigid-body assumptions. This paper addresses this problem and enables the extension of existing rigid-body pose estimation methods to non-rigid systems. Our approach integrates two core components: first, we capture elastic properties using a deformation-force model, efficiently learned via a Multi-Layer Perceptron; second, we resolve the platform's inherently smooth motion using continuous-time B-spline kinematic models. By continuously applying Newton's Second Law, our method formulates the relationship between visually-derived trajectory acceleration and predicted deformation-induced acceleration. We demonstrate that our approach not only enables robust and accurate pose estimation on non-rigid platforms, but also shows that the properly modeled platform physics allow for the recovery of inertial sensing properties. We validate this feasibility on a simple spring-camera system, showing how it robustly resolves the typically ill-posed problem of metric scale and gravity recovery in monocular visual odometry.

Jianwen Jiang, Gaojie Lin, Zhengkun Rong et al.

Existing neural head avatars methods have achieved significant progress in the image quality and motion range of portrait animation. However, these methods neglect the computational overhead, and to the best of our knowledge, none is designed to run on mobile devices. This paper presents MobilePortrait, a lightweight one-shot neural head avatars method that reduces learning complexity by integrating external knowledge into both the motion modeling and image synthesis, enabling real-time inference on mobile devices. Specifically, we introduce a mixed representation of explicit and implicit keypoints for precise motion modeling and precomputed visual features for enhanced foreground and background synthesis. With these two key designs and using simple U-Nets as backbones, our method achieves state-of-the-art performance with less than one-tenth the computational demand. It has been validated to reach speeds of over 100 FPS on mobile devices and support both video and audio-driven inputs.

Zhen Li, Lingli Wang, Mofang Cheng et al.

We present a efficient multi-view inverse rendering method for large-scale real-world indoor scenes that reconstructs global illumination and physically-reasonable SVBRDFs. Unlike previous representations, where the global illumination of large scenes is simplified as multiple environment maps, we propose a compact representation called Texture-based Lighting (TBL). It consists of 3D mesh and HDR textures, and efficiently models direct and infinite-bounce indirect lighting of the entire large scene. Based on TBL, we further propose a hybrid lighting representation with precomputed irradiance, which significantly improves the efficiency and alleviates the rendering noise in the material optimization. To physically disentangle the ambiguity between materials, we propose a three-stage material optimization strategy based on the priors of semantic segmentation and room segmentation. Extensive experiments show that the proposed method outperforms the state-of-the-art quantitatively and qualitatively, and enables physically-reasonable mixed-reality applications such as material editing, editable novel view synthesis and relighting. The project page is at https://lzleejean.github.io/TexIR.

Zhaoshuai Qi, Yifeng Hao, Rui Hu et al.

Structured light-based method with a camera-projector pair (CPP) plays a vital role in indoor 3D reconstruction, especially for scenes with weak textures. Previous methods usually assume known intrinsics, which are pre-calibrated from known objects, or self-calibrated from multi-view observations. It is still challenging to reliably recover CPP intrinsics from only two views without any known objects. In this paper, we provide a simple yet reliable solution. We demonstrate that, for the first time, sufficient constraints on CPP intrinsics can be derived from an unknown cuboid corner (C2), e.g. a room's corner, which is a common structure in indoor scenes. In addition, with only known camera principal point, the complex multi-variable estimation of all CPP intrinsics can be simplified to a simple univariable optimization problem, leading to reliable calibration and thus direct 3D reconstruction with unknown CPP. Extensive results have demonstrated the superiority of the proposed method over both traditional and learning-based counterparts. Furthermore, the proposed method also demonstrates impressive potential to solve similar tasks without active lighting, such as sparse-view structure from motion.

Huajian Zeng, Chaohua Yao, Yuantai Zhang et al.

Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy learning, where wrist trajectories track the end-effector and finger articulations specify the grasp pose. Two major challenges arise in this setting: hands frequently leave the camera view for extended periods due to head motion, and persistent hand-object interactions cause severe occlusions of one or both hands. Existing methods uniformly condition on noisy hand motion observations without accounting for their per-frame reliability, leading to substantial performance degradation. Our key insight is that accurate world space hand motion estimation is tightly coupled with the quality of per-frame hand observations. To this end, we decompose the quality of hand motion observations extracted from an off-the-shelf hand pose estimator into four channels: wrist global translation and finger articulations for both hands. We propose StableHand, a quality-aware flow-matching framework conditioned on these four-channel quality signals, which are predicted by a learned quality network. We naturally incorporate the quality signals into the flow-matching process through a per-channel forward schedule, a quality-adjusted velocity target, AdaLN modulation of the DiT denoiser, and a quality-aware ODE initialization. This unified generative process preserves high-quality observations while reconstructing unreliable ones using a learned bimanual motion prior. Experiments on HOT3D and ARCTIC, two egocentric benchmarks featuring long missing-hand spans and persistent hand-object occlusions, show that StableHand achieves state-of-the-art performance across all reported metrics, reducing W-MPJPE by 20-25% compared to the strongest baseline, with the largest gains on heavily occluded ARCTIC sequences.

Jinheng Xie, Jiajun Feng, Zhaoxu Tian et al.

Concepts involved in long-form videos such as people, objects, and their interactions, can be viewed as following an implicit prior. They are notably complex and continue to pose challenges to be comprehensively learned. In recent years, generative pre-training (GPT) has exhibited versatile capacities in modeling any kind of text content even visual locations. Can this manner work for learning long-form video prior? Instead of operating on pixel space, it is efficient to employ visual locations like bounding boxes and keypoints to represent key information in videos, which can be simply discretized and then tokenized for consumption by GPT. Due to the scarcity of suitable data, we create a new dataset called \textbf{Storyboard20K} from movies to serve as a representative. It includes synopses, shot-by-shot keyframes, and fine-grained annotations of film sets and characters with consistent IDs, bounding boxes, and whole body keypoints. In this way, long-form videos can be represented by a set of tokens and be learned via generative pre-training. Experimental results validate that our approach has great potential for learning long-form video prior. Code and data will be released at \url{https://github.com/showlab/Long-form-Video-Prior}.

Jiaqi Yang, Yaning Zhang, Jingxi Hu et al.

While large visual models (LVM) demonstrated significant potential in image understanding, due to the application of large-scale pre-training, the Segment Anything Model (SAM) has also achieved great success in the field of image segmentation, supporting flexible interactive cues and strong learning capabilities. However, SAM's performance often falls short in cross-domain and few-shot applications. Previous work has performed poorly in transferring prior knowledge from base models to new applications. To tackle this issue, we propose a task-adaptive auto-visual prompt framework, a new paradigm for Cross-dominan Few-shot segmentation (CD-FSS). First, a Multi-level Feature Fusion (MFF) was used for integrated feature extraction as prior knowledge. Besides, we incorporate a Class Domain Task-Adaptive Auto-Prompt (CDTAP) module to enable class-domain agnostic feature extraction and generate high-quality, learnable visual prompts. This significant advancement uses a unique generative approach to prompts alongside a comprehensive model structure and specialized prototype computation. While ensuring that the prior knowledge of SAM is not discarded, the new branch disentangles category and domain information through prototypes, guiding it in adapting the CD-FSS. Comprehensive experiments across four cross-domain datasets demonstrate that our model outperforms the state-of-the-art CD-FSS approach, achieving an average accuracy improvement of 1.3\% in the 1-shot setting and 11.76\% in the 5-shot setting.

Jiaqi Yang, Chu'ai Zhang, Zhengbao Wang et al.

3D point cloud registration is a fundamental problem in computer vision, computer graphics, robotics, remote sensing, and etc. Over the last thirty years, we have witnessed the amazing advancement in this area with numerous kinds of solutions. Although a handful of relevant surveys have been conducted, their coverage is still limited. In this work, we present a comprehensive survey on 3D point cloud registration, covering a set of sub-areas such as pairwise coarse registration, pairwise fine registration, multi-view registration, cross-scale registration, and multi-instance registration. The datasets, evaluation metrics, method taxonomy, discussions of the merits and demerits, insightful thoughts of future directions are comprehensively presented in this survey. The regularly updated project page of the survey is available at https://github.com/Amyyyy11/3D-Registration-in-30-Years-A-Survey.

Jun Wu, Jicun Li, Jiaqi Yang et al.

Circuit cutting enables large quantum circuits to run on small NISQ devices, but it introduces an exponentially high sampling overhead. Here, we present CutVQA, a co-design framework that integrates circuit cutting with quantum architecture search to scale VQAs. CutVQA performs cutting-aware architecture search and applies subcircuit-level optimization enabled by parameter locality, reducing both reconstruction and training overhead. Evaluations on two representative VQAs (QAOA and VQE) show that CutVQA matches baseline accuracy while reducing sampling overhead by 2-3 orders of magnitude and shortening training time by at least 50%, demonstrating that co-design is essential for scaling VQA execution.

Zhenxuan Zeng, Qiao Wu, Xiyu Zhang et al.

In real-world environments, a LiDAR point cloud registration method with robust generalization capabilities (across varying distances and datasets) is crucial for ensuring safety in autonomous driving and other LiDAR-based applications. However, current methods fall short in achieving this level of generalization. To address these limitations, we propose UGP, a pruned framework designed to enhance generalization power for LiDAR point cloud registration. The core insight in UGP is the elimination of cross-attention mechanisms to improve generalization, allowing the network to concentrate on intra-frame feature extraction. Additionally, we introduce a progressive self-attention module to reduce ambiguity in large-scale scenes and integrate Bird's Eye View (BEV) features to incorporate semantic information about scene elements. Together, these enhancements significantly boost the network's generalization performance. We validated our approach through various generalization experiments in multiple outdoor scenes. In cross-distance generalization experiments on KITTI and nuScenes, UGP achieved state-of-the-art mean Registration Recall rates of 94.5% and 91.4%, respectively. In cross-dataset generalization from nuScenes to KITTI, UGP achieved a state-of-the-art mean Registration Recall of 90.9%. Code will be available at https://github.com/peakpang/UGP.

Di Wang, Meiqi Hu, Yao Jin et al.

Accurate hyperspectral image (HSI) interpretation is critical for providing valuable insights into various earth observation-related applications such as urban planning, precision agriculture, and environmental monitoring. However, existing HSI processing methods are predominantly task-specific and scene-dependent, which severely limits their ability to transfer knowledge across tasks and scenes, thereby reducing the practicality in real-world applications. To address these challenges, we present HyperSIGMA, a vision transformer-based foundation model that unifies HSI interpretation across tasks and scenes, scalable to over one billion parameters. To overcome the spectral and spatial redundancy inherent in HSIs, we introduce a novel sparse sampling attention (SSA) mechanism, which effectively promotes the learning of diverse contextual features and serves as the basic block of HyperSIGMA. HyperSIGMA integrates spatial and spectral features using a specially designed spectral enhancement module. In addition, we construct a large-scale hyperspectral dataset, HyperGlobal-450K, for pre-training, which contains about 450K hyperspectral images, significantly surpassing existing datasets in scale. Extensive experiments on various high-level and low-level HSI tasks demonstrate HyperSIGMA's versatility and superior representational capability compared to current state-of-the-art methods. Moreover, HyperSIGMA shows significant advantages in scalability, robustness, cross-modal transferring capability, real-world applicability, and computational efficiency. The code and models will be released at https://github.com/WHU-Sigma/HyperSIGMA.

Gaojie Lin, Jianwen Jiang, Jiaqi Yang et al.

End-to-end human animation, such as audio-driven talking human generation, has undergone notable advancements in the recent few years. However, existing methods still struggle to scale up as large general video generation models, limiting their potential in real applications. In this paper, we propose OmniHuman, a Diffusion Transformer-based framework that scales up data by mixing motion-related conditions into the training phase. To this end, we introduce two training principles for these mixed conditions, along with the corresponding model architecture and inference strategy. These designs enable OmniHuman to fully leverage data-driven motion generation, ultimately achieving highly realistic human video generation. More importantly, OmniHuman supports various portrait contents (face close-up, portrait, half-body, full-body), supports both talking and singing, handles human-object interactions and challenging body poses, and accommodates different image styles. Compared to existing end-to-end audio-driven methods, OmniHuman not only produces more realistic videos, but also offers greater flexibility in inputs. It also supports multiple driving modalities (audio-driven, video-driven and combined driving signals). Video samples are provided on the ttfamily project page (https://omnihuman-lab.github.io)

Tangtangfang Fang, Yang Jiao, Xiangjian He et al.

Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasing subtle anatomical details. In this paper, we present TAFG-MAN, a latent diffusion framework for efficient and high-quality LDCT image denoising. The framework combines a perceptually optimized autoencoder, conditional latent diffusion restoration in a compact latent space, and a lightweight Timestep-Adaptive Frequency-Gated (TAFG) conditioning design. TAFG decomposes condition features into low- and high-frequency components, predicts timestep-adaptive gates from the current denoising feature and timestep embedding, and progressively releases high-frequency guidance in later denoising stages before cross-attention. In this way, the model relies more on stable structural guidance at early reverse steps and introduces fine details more cautiously as denoising proceeds, improving the balance between noise suppression and detail preservation. Experiments show that TAFG-MAN achieves a favorable quality-efficiency trade-off against representative baselines. Compared with its base variant without TAFG, it further improves detail preservation and perceptual quality while maintaining essentially the same inference cost, and ablation results confirm the effectiveness of the proposed conditioning mechanism.

Rong Liu, Junye Liang, Jiaqi Yang et al.

Due to the difficulty of obtaining labeled data for hyperspectral images (HSIs), cross-scene classification has emerged as a widely adopted approach in the remote sensing community. It involves training a model using labeled data from a source domain (SD) and unlabeled data from a target domain (TD), followed by inferencing on the TD. However, variations in the reflectance spectrum of the same object between the SD and the TD, as well as differences in the feature distribution of the same land cover class, pose significant challenges to the performance of cross-scene classification. To address this issue, we propose a dual classification head self-training network (DHSNet). This method aligns class-wise features across domains, ensuring that the trained classifier can accurately classify TD data of different classes. We introduce a dual classification head self-training strategy for the first time in the cross-scene HSI classification field. The proposed approach mitigates domain gap while preventing the accumulation of incorrect pseudo-labels in the model. Additionally, we incorporate a novel central feature attention mechanism to enhance the model's capacity to learn scene-invariant features across domains. Experimental results on three cross-scene HSI datasets demonstrate that the proposed DHSNET significantly outperforms other state-of-the-art approaches. The code for DHSNet will be available at https://github.com/liurongwhm.

Yaorui Shi, Jiaqi Yang, Changhao Nai et al.

Single-cell RNA sequencing (scRNA-seq) offers detailed insights into cellular heterogeneity. Recent advancements leverage single-cell large language models (scLLMs) for effective representation learning. These models focus exclusively on transcriptomic data, neglecting complementary biological knowledge from textual descriptions. To overcome this limitation, we propose scMMGPT, a novel multimodal framework designed for language-enhanced representation learning in single-cell transcriptomics. Unlike existing methods, scMMGPT employs robust cell representation extraction, preserving quantitative gene expression data, and introduces an innovative two-stage pre-training strategy combining discriminative precision with generative flexibility. Extensive experiments demonstrate that scMMGPT significantly outperforms unimodal and multimodal baselines across key downstream tasks, including cell annotation and clustering, and exhibits superior generalization in out-of-distribution scenarios.

Zhenzhi Wang, Jiaqi Yang, Jianwen Jiang et al.

End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could only animate a single subject and inject conditions in a global manner, ignoring scenarios that multiple concepts could appears in the same video with rich human-human interactions and human-object interactions. Such global assumption prevents precise and per-identity control of multiple concepts including humans and objects, therefore hinders applications. In this work, we discard the single-entity assumption and introduce a novel framework that enforces strong, region-specific binding of conditions from modalities to each identity's spatiotemporal footprint. Given reference images of multiple concepts, our method could automatically infer layout information by leveraging a mask predictor to match appearance cues between the denoised video and each reference appearance. Furthermore, we inject local audio condition into its corresponding region to ensure layout-aligned modality matching in a iterative manner. This design enables the high-quality generation of controllable multi-concept human-centric videos. Empirical results and ablation studies validate the effectiveness of our explicit layout control for multi-modal conditions compared to implicit counterparts and other existing methods.

Jiaqi Yang, Wei Xie, Xiaohua Xu

Quantum neural networks (QNNs) play an important role as an emerging technology in the rapidly growing field of quantum machine learning. While their empirical success is evident, the theoretical explorations of QNNs, particularly their generalization properties, are less developed and primarily focus on the uniform convergence approach. In this paper, we exploit an advanced tool in classical learning theory, i.e., algorithmic stability, to study the generalization of QNNs. We first establish high-probability generalization bounds for QNNs via uniform stability. Our bounds shed light on the key factors influencing the generalization performance of QNNs and provide practical insights into both the design and training processes. We next explore the generalization of QNNs on near-term noisy intermediate-scale quantum (NISQ) devices, highlighting the potential benefits of quantum noise. Moreover, we argue that our previous analysis characterizes worst-case generalization guarantees, and we establish a refined optimization-dependent generalization bound for QNNs via on-average stability. Numerical experiments on various real-world datasets support our theoretical findings.

Siwen Quan, Junhao Yu, Ziming Nie et al.

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and incompleteness. This poses great challenges to down-stream point cloud processing tasks. In recent years, deep-learning-based point cloud enhancement methods, which aim to achieve dense, clean, and complete point clouds from low-quality raw point clouds using deep neural networks, are gaining tremendous research attention. This paper, for the first time to our knowledge, presents a comprehensive survey for deep-learning-based point cloud enhancement methods. It covers three main perspectives for point cloud enhancement, i.e., (1) denoising to achieve clean data; (2) completion to recover unseen data; (3) upsampling to obtain dense data. Our survey presents a new taxonomy for recent state-of-the-art methods and systematic experimental results on standard benchmarks. In addition, we share our insightful observations, thoughts, and inspiring future research directions for point cloud enhancement with deep learning.

Jiaqi Yang, Enming Liang, Zicheng Su et al.

Decision-focused learning (DFL) offers an end-to-end approach to the predict-then-optimize (PO) framework by training predictive models directly on decision loss (DL), enhancing decision-making performance within PO contexts. However, the implementation of DFL poses distinct challenges. Primarily, DL can result in deviation from the physical significance of the predictions under limited data. Additionally, some predictive models are non-differentiable or black-box, which cannot be adjusted using gradient-based methods. To tackle the above challenges, we propose a novel framework, Decision-Focused Fine-tuning (DFF), which embeds the DFL module into the PO pipeline via a novel bias correction module. DFF is formulated as a constrained optimization problem that maintains the proximity of the DL-enhanced model to the original predictive model within a defined trust region. We theoretically prove that DFF strictly confines prediction bias within a predetermined upper bound, even with limited datasets, thereby substantially reducing prediction shifts caused by DL under limited data. Furthermore, the bias correction module can be integrated into diverse predictive models, enhancing adaptability to a broad range of PO tasks. Extensive evaluations on synthetic and real-world datasets, including network flow, portfolio optimization, and resource allocation problems with different predictive models, demonstrate that DFF not only improves decision performance but also adheres to fine-tuning constraints, showcasing robust adaptability across various scenarios.

Tianyun Zhong, Chao Liang, Jianwen Jiang et al.

Diffusion-based audio-driven talking avatar methods have recently gained attention for their high-fidelity, vivid, and expressive results. However, their slow inference speed limits practical applications. Despite the development of various distillation techniques for diffusion models, we found that naive diffusion distillation methods do not yield satisfactory results. Distilled models exhibit reduced robustness with open-set input images and a decreased correlation between audio and video compared to teacher models, undermining the advantages of diffusion models. To address this, we propose FADA (Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation). We first designed a mixed-supervised loss to leverage data of varying quality and enhance the overall model capability as well as robustness. Additionally, we propose a multi-CFG distillation with learnable tokens to utilize the correlation between audio and reference image conditions, reducing the threefold inference runs caused by multi-CFG with acceptable quality degradation. Extensive experiments across multiple datasets show that FADA generates vivid videos comparable to recent diffusion model-based methods while achieving an NFE speedup of 4.17-12.5 times. Demos are available at our webpage http://fadavatar.github.io.

Chao Liang, Jianwen Jiang, Wang Liao et al.

Recent advancements in human video generation and animation tasks, driven by diffusion models, have achieved significant progress. However, expressive and realistic human animation remains challenging due to the trade-off between motion naturalness and visual fidelity. To address this, we propose \textbf{AlignHuman}, a framework that combines Preference Optimization as a post-training technique with a divide-and-conquer training strategy to jointly optimize these competing objectives. Our key insight stems from an analysis of the denoising process across timesteps: (1) early denoising timesteps primarily control motion dynamics, while (2) fidelity and human structure can be effectively managed by later timesteps, even if early steps are skipped. Building on this observation, we propose timestep-segment preference optimization (TPO) and introduce two specialized LoRAs as expert alignment modules, each targeting a specific dimension in its corresponding timestep interval. The LoRAs are trained using their respective preference data and activated in the corresponding intervals during inference to enhance motion naturalness and fidelity. Extensive experiments demonstrate that AlignHuman improves strong baselines and reduces NFEs during inference, achieving a 3.3$\times$ speedup (from 100 NFEs to 30 NFEs) with minimal impact on generation quality. Homepage: \href{https://alignhuman.github.io/}{https://alignhuman.github.io/}

Quanwei Liu, Tao Huang, Yanni Dong et al.

Remote sensing images (RSIs) capture both natural and human-induced changes on the Earth's surface, serving as essential data for environmental monitoring, urban planning, and resource management. Semantic segmentation (SS) of RSIs enables the fine-grained interpretation of surface features, making it a critical task in remote sensing analysis. With the increasing diversity and volume of RSIs collected by sensors on various platforms, traditional processing methods struggle to maintain efficiency and accuracy. In response, deep learning (DL) has emerged as a transformative approach, enabling substantial advances in remote sensing image semantic segmentation (RSISS) by automating feature extraction and improving segmentation accuracy across diverse modalities. This paper revisits the evolution of DL-based RSISS by categorizing existing approaches into four stages: the early pixel-based methods, the prevailing patch-based and tile-based techniques, and the emerging image-based strategies enabled by foundation models. We analyze these developments from the perspective of feature extraction and learning strategies, revealing the field's progression from pixel-level to tile-level and from unimodal to multimodal segmentation. Furthermore, we conduct a comprehensive evaluation of nearly 40 advanced techniques on a unified dataset to quantitatively characterize their performance and applicability. This review offers a holistic view of DL-based SS for RS, highlighting key advancements, comparative insights, and open challenges to guide future research.

Chao Liang, Jianwen Jiang, Tianyun Zhong et al.

Talking face generation technology creates talking videos from arbitrary appearance and motion signal, with the "arbitrary" offering ease of use but also introducing challenges in practical applications. Existing methods work well with standard inputs but suffer serious performance degradation with intricate real-world ones. Moreover, efficiency is also an important concern in deployment. To comprehensively address these issues, we introduce SuperFace, a teacher-student framework that balances quality, robustness, cost and editability. We first propose a simple but effective teacher model capable of handling inputs of varying qualities to generate high-quality results. Building on this, we devise an efficient distillation strategy to acquire an identity-specific student model that maintains quality with significantly reduced computational load. Our experiments validate that SuperFace offers a more comprehensive solution than existing methods for the four mentioned objectives, especially in reducing FLOPs by 99\% with the student model. SuperFace can be driven by both video and audio and allows for localized facial attributes editing.

Jiaqi Yang, Nitish Mehta, Xiaoling Hu et al.

Accurate segmentation of Optical Coherence Tomography (OCT) images is crucial for diagnosing and monitoring retinal diseases. However, the labor-intensive nature of pixel-level annotation limits the scalability of supervised learning with large datasets. Weakly Supervised Semantic Segmentation (WSSS) provides a promising alternative by leveraging image-level labels. In this study, we propose a novel WSSS approach that integrates structural guidance with text-driven strategies to generate high-quality pseudo labels, significantly improving segmentation performance. In terms of visual information, our method employs two processing modules that exchange raw image features and structural features from OCT images, guiding the model to identify where lesions are likely to occur. In terms of textual information, we utilize large-scale pretrained models from cross-domain sources to implement label-informed textual guidance and synthetic descriptive integration with two textual processing modules that combine local semantic features with consistent synthetic descriptions. By fusing these visual and textual components within a multimodal framework, our approach enhances lesion localization accuracy. Experimental results on three OCT datasets demonstrate that our method achieves state-of-the-art performance, highlighting its potential to improve diagnostic accuracy and efficiency in medical imaging.

Jiaming Deng, Zhenglin Chen, Minjiang Chen et al.

Mycoplasma pneumoniae pneumonia (MPP) poses significant diagnostic challenges in pediatric healthcare, especially in regions like China where it's prevalent. We introduce PneumoniaAPP, a mobile application leveraging deep learning techniques for rapid MPP detection. Our approach capitalizes on convolutional neural networks (CNNs) trained on a comprehensive dataset comprising 3345 chest X-ray (CXR) images, which includes 833 CXR images revealing MPP and additionally augmented with samples from a public dataset. The CNN model achieved an accuracy of 88.20% and an AUROC of 0.9218 across all classes, with a specific accuracy of 97.64% for the mycoplasma class, as demonstrated on the testing dataset. Furthermore, we integrated explainability techniques into PneumoniaAPP to aid respiratory physicians in lung opacity localization. Our contribution extends beyond existing research by targeting pediatric MPP, emphasizing the age group of 0-12 years, and prioritizing deployment on mobile devices. This work signifies a significant advancement in pediatric pneumonia diagnosis, offering a reliable and accessible tool to alleviate diagnostic burdens in healthcare settings.

Jianwen Jiang, Weihong Zeng, Zerong Zheng et al.

Existing video avatar models can produce fluid human animations, yet they struggle to move beyond mere physical likeness to capture a character's authentic essence. Their motions typically synchronize with low-level cues like audio rhythm, lacking a deeper semantic understanding of emotion, intent, or context. To bridge this gap, \textbf{we propose a framework designed to generate character animations that are not only physically plausible but also semantically coherent and expressive.} Our model, \textbf{OmniHuman-1.5}, is built upon two key technical contributions. First, we leverage Multimodal Large Language Models to synthesize a structured textual representation of conditions that provides high-level semantic guidance. This guidance steers our motion generator beyond simplistic rhythmic synchronization, enabling the production of actions that are contextually and emotionally resonant. Second, to ensure the effective fusion of these multimodal inputs and mitigate inter-modality conflicts, we introduce a specialized Multimodal DiT architecture with a novel Pseudo Last Frame design. The synergy of these components allows our model to accurately interpret the joint semantics of audio, images, and text, thereby generating motions that are deeply coherent with the character, scene, and linguistic content. Extensive experiments demonstrate that our model achieves leading performance across a comprehensive set of metrics, including lip-sync accuracy, video quality, motion naturalness and semantic consistency with textual prompts. Furthermore, our approach shows remarkable extensibility to complex scenarios, such as those involving multi-person and non-human subjects. Homepage: \href{https://omnihuman-lab.github.io/v1_5/}

Jiaqi Yang, Wenting Chen, Xiaohan Xing et al.

Multimodal learning that integrates histopathology images and genomic data holds great promise for cancer survival prediction. However, existing methods face key limitations: 1) They rely on multimodal mapping and metrics in Euclidean space, which cannot fully capture the hierarchical structures in histopathology (among patches from different resolutions) and genomics data (from genes to pathways). 2) They discretize survival time into independent risk intervals, which ignores its continuous and ordinal nature and fails to achieve effective optimization. 3) They treat censorship as a binary indicator, excluding censored samples from model optimization and not making full use of them. To address these challenges, we propose HySurvPred, a novel framework for survival prediction that integrates three key modules: Multimodal Hyperbolic Mapping (MHM), Angle-aware Ranking-based Contrastive Loss (ARCL) and Censor-Conditioned Uncertainty Constraint (CUC). Instead of relying on Euclidean space, we design the MHM module to explore the inherent hierarchical structures within each modality in hyperbolic space. To better integrate multimodal features in hyperbolic space, we introduce the ARCL module, which uses ranking-based contrastive learning to preserve the ordinal nature of survival time, along with the CUC module to fully explore the censored data. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on five benchmark datasets. The source code is to be released.

Yuanhong Yu, Xingyi He, Chen Zhao et al.

This paper presents a generalizable RGB-based approach for object pose estimation, specifically designed to address challenges in sparse-view settings. While existing methods can estimate the poses of unseen objects, their generalization ability remains limited in scenarios involving occlusions and sparse reference views, restricting their real-world applicability. To overcome these limitations, we introduce corner points of the object bounding box as an intermediate representation of the object pose. The 3D object corners can be reliably recovered from sparse input views, while the 2D corner points in the target view are estimated through a novel reference-based point synthesizer, which works well even in scenarios involving occlusions. As object semantic points, object corners naturally establish 2D-3D correspondences for object pose estimation with a PnP algorithm. Extensive experiments on the YCB-Video and Occluded-LINEMOD datasets show that our approach outperforms state-of-the-art methods, highlighting the effectiveness of the proposed representation and significantly enhancing the generalization capabilities of object pose estimation, which is crucial for real-world applications.