Zhihang Zhong

Xiaolin Liu, Yilun Zhu, Xiangyu Zhao et al.

Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored. Many practical questions are determined by momentary visual events: localized actions or state transitions that may last only a few frames. Such evidence can be skipped by sparse frame sampling, suppressed by visual-token compression, or diluted by coarse temporal aggregation, causing failures that language-side reasoning cannot reliably recover. We introduce Moment-Video, a benchmark for diagnosing the temporal fidelity of video MLLMs through momentary visual event understanding. Each question is grounded in a localized, visually observable, and sampling-sensitive event, requiring models to notice, count, describe, or reason about transient evidence rather than rely on persistent objects, global scene context, or language priors. Moment-Video contains 1,000 human-verified video-QA pairs across 7 domains and 25 fine-grained subcategories, covering four task types: Temporal Occurrence, Temporal Counting, Action Description, and Temporal Reasoning. We evaluate 33 proprietary and open-source MLLMs on Moment-Video. The best-performing model, Seed-2.0-Pro, achieves only 39.6% overall accuracy, while most open-source models remain below 25%, revealing a substantial gap in momentary visual event understanding. Diagnostic analyses show that denser frame sampling improves some models but does not eliminate the bottleneck, and longer videos introduce stronger temporal-localization challenges. These findings suggest that current video MLLMs still lack temporally faithful representations for capturing, preserving, and using brief but decisive visual evidence.

Zhihang Zhong, Mingdeng Cao, Xiang Ji et al.

This paper studies the challenging problem of recovering motion from blur, also known as joint deblurring and interpolation or blur temporal super-resolution. The challenges are twofold: 1) the current methods still leave considerable room for improvement in terms of visual quality even on the synthetic dataset, and 2) poor generalization to real-world data. To this end, we propose a blur interpolation transformer (BiT) to effectively unravel the underlying temporal correlation encoded in blur. Based on multi-scale residual Swin transformer blocks, we introduce dual-end temporal supervision and temporally symmetric ensembling strategies to generate effective features for time-varying motion rendering. In addition, we design a hybrid camera system to collect the first real-world dataset of one-to-many blur-sharp video pairs. Experimental results show that BiT has a significant gain over the state-of-the-art methods on the public dataset Adobe240. Besides, the proposed real-world dataset effectively helps the model generalize well to real blurry scenarios. Code and data are available at https://github.com/zzh-tech/BiT.

Zhihang Zhong, Xiao Sun, Zhirong Wu et al.

We study the challenging problem of recovering detailed motion from a single motion-blurred image. Existing solutions to this problem estimate a single image sequence without considering the motion ambiguity for each region. Therefore, the results tend to converge to the mean of the multi-modal possibilities. In this paper, we explicitly account for such motion ambiguity, allowing us to generate multiple plausible solutions all in sharp detail. The key idea is to introduce a motion guidance representation, which is a compact quantization of 2D optical flow with only four discrete motion directions. Conditioned on the motion guidance, the blur decomposition is led to a specific, unambiguous solution by using a novel two-stage decomposition network. We propose a unified framework for blur decomposition, which supports various interfaces for generating our motion guidance, including human input, motion information from adjacent video frames, and learning from a video dataset. Extensive experiments on synthesized datasets and real-world data show that the proposed framework is qualitatively and quantitatively superior to previous methods, and also offers the merit of producing physically plausible and diverse solutions. Code is available at https://github.com/zzh-tech/Animation-from-Blur.

Zhihang Zhong, Mingdeng Cao, Xiao Sun et al.

Rolling shutter (RS) distortion can be interpreted as the result of picking a row of pixels from instant global shutter (GS) frames over time during the exposure of the RS camera. This means that the information of each instant GS frame is partially, yet sequentially, embedded into the row-dependent distortion. Inspired by this fact, we address the challenging task of reversing this process, i.e., extracting undistorted GS frames from images suffering from RS distortion. However, since RS distortion is coupled with other factors such as readout settings and the relative velocity of scene elements to the camera, models that only exploit the geometric correlation between temporally adjacent images suffer from poor generality in processing data with different readout settings and dynamic scenes with both camera motion and object motion. In this paper, instead of two consecutive frames, we propose to exploit a pair of images captured by dual RS cameras with reversed RS directions for this highly challenging task. Grounded on the symmetric and complementary nature of dual reversed distortion, we develop a novel end-to-end model, IFED, to generate dual optical flow sequence through iterative learning of the velocity field during the RS time. Extensive experimental results demonstrate that IFED is superior to naive cascade schemes, as well as the state-of-the-art which utilizes adjacent RS images. Most importantly, although it is trained on a synthetic dataset, IFED is shown to be effective at retrieving GS frame sequences from real-world RS distorted images of dynamic scenes. Code is available at https://github.com/zzh-tech/Dual-Reversed-RS.

Muyao Niu, Zhuoxiao Li, Zhihang Zhong et al.

Seeing-in-the-dark is one of the most important and challenging computer vision tasks due to its wide applications and extreme complexities of in-the-wild scenarios. Existing arts can be mainly divided into two threads: 1) RGB-dependent methods restore information using degraded RGB inputs only (\eg, low-light enhancement), 2) RGB-independent methods translate images captured under auxiliary near-infrared (NIR) illuminants into RGB domain (\eg, NIR2RGB translation). The latter is very attractive since it works in complete darkness and the illuminants are visually friendly to naked eyes, but tends to be unstable due to its intrinsic ambiguities. In this paper, we try to robustify NIR2RGB translation by designing the optimal spectrum of auxiliary illumination in the wide-band VIS-NIR range, while keeping visual friendliness. Our core idea is to quantify the visibility constraint implied by the human vision system and incorporate it into the design pipeline. By modeling the formation process of images in the VIS-NIR range, the optimal multiplexing of a wide range of LEDs is automatically designed in a fully differentiable manner, within the feasible region defined by the visibility constraint. We also collect a substantially expanded VIS-NIR hyperspectral image dataset for experiments by using a customized 50-band filter wheel. Experimental results show that the task can be significantly improved by using the optimized wide-band illumination than using NIR only. Codes Available: https://github.com/MyNiuuu/VCSD.

Mingxin Liu, Ziqian Fan, Zhaokai Wang et al.

Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense reasoning, offering limited assessment of this capability under structured, domain-specific constraints. In this work, we introduce GRADE, the first benchmark to assess discipline-informed knowledge and reasoning in image editing. GRADE comprises 520 carefully curated samples across 10 academic domains, spanning from natural science to social science. To support rigorous evaluation, we propose a multi-dimensional evaluation protocol that jointly assesses Discipline Reasoning, Visual Consistency, and Logical Readability. Extensive experiments on 20 state-of-the-art open-source and closed-source models reveal substantial limitations in current models under implicit, knowledge-intensive editing settings, leading to large performance gaps. Beyond quantitative scores, we conduct rigorous analyses and ablations to expose model shortcomings and identify the constraints within disciplinary editing. Together, GRADE pinpoints key directions for the future development of unified multimodal models, advancing the research on discipline-informed image editing and reasoning. Our benchmark and evaluation code are publicly released.

Yusheng Wang, Yunfan Lu, Ye Gao et al.

Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the information from clear regions in adjacent frames for current frame deblurring. To realize this process, our idea is to detect the pixel-wise blur level of each frame and combine it with video deblurring. To this end, we propose a novel framework that utilizes the motion magnitude prior (MMP) as guidance for efficient deep video deblurring. Specifically, as the pixel movement along its trajectory during the exposure time is positively correlated to the level of motion blur, we first use the average magnitude of optical flow from the high-frequency sharp frames to generate the synthetic blurry frames and their corresponding pixel-wise motion magnitude maps. We then build a dataset including the blurry frame and MMP pairs. The MMP is then learned by a compact CNN by regression. The MMP consists of both spatial and temporal blur level information, which can be further integrated into an efficient recurrent neural network (RNN) for video deblurring. We conduct intensive experiments to validate the effectiveness of the proposed methods on the public datasets.

Mingdeng Cao, Zhihang Zhong, Jiahao Wang et al.

This paper proposes the first real-world rolling shutter (RS) correction dataset, BS-RSC, and a corresponding model to correct the RS frames in a distorted video. Mobile devices in the consumer market with CMOS-based sensors for video capture often result in rolling shutter effects when relative movements occur during the video acquisition process, calling for RS effect removal techniques. However, current state-of-the-art RS correction methods often fail to remove RS effects in real scenarios since the motions are various and hard to model. To address this issue, we propose a real-world RS correction dataset BS-RSC. Real distorted videos with corresponding ground truth are recorded simultaneously via a well-designed beam-splitter-based acquisition system. BS-RSC contains various motions of both camera and objects in dynamic scenes. Further, an RS correction model with adaptive warping is proposed. Our model can warp the learned RS features into global shutter counterparts adaptively with predicted multiple displacement fields. These warped features are aggregated and then reconstructed into high-quality global shutter frames in a coarse-to-fine strategy. Experimental results demonstrate the effectiveness of the proposed method, and our dataset can improve the model's ability to remove the RS effects in the real world.

Zhihang Zhong, Mingxi Cheng, Zhirong Wu et al.

Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially when the composition of the input image is complex. Moreover, labeling of cropping data is costly and hence the amount of data is limited, leading to poor generalization performance of current algorithms in the wild. In this work, we take advantage of vision-language models as a foundation for creating robust and user-intentional cropping algorithms. By adapting a transformer decoder with a pre-trained CLIP-based detection model, OWL-ViT, we develop a method to perform cropping with a text or image query that reflects the user's intention as guidance. In addition, our pipeline design allows the model to learn text-conditioned aesthetic cropping with a small cropping dataset, while inheriting the open-vocabulary ability acquired from millions of text-image pairs. We validate our model through extensive experiments on existing datasets as well as a new cropping test set we compiled that is characterized by content ambiguity.

Mingdeng Cao, Zhihang Zhong, Yanbo Fan et al.

This paper aims at exploring how to synthesize close-to-real blurs that existing video deblurring models trained on them can generalize well to real-world blurry videos. In recent years, deep learning-based approaches have achieved promising success on video deblurring task. However, the models trained on existing synthetic datasets still suffer from generalization problems over real-world blurry scenarios with undesired artifacts. The factors accounting for the failure remain unknown. Therefore, we revisit the classical blur synthesis pipeline and figure out the possible reasons, including shooting parameters, blur formation space, and image signal processor~(ISP). To analyze the effects of these potential factors, we first collect an ultra-high frame-rate (940 FPS) RAW video dataset as the data basis to synthesize various kinds of blurs. Then we propose a novel realistic blur synthesis pipeline termed as RAW-Blur by leveraging blur formation cues. Through numerous experiments, we demonstrate that synthesizing blurs in the RAW space and adopting the same ISP as the real-world testing data can effectively eliminate the negative effects of synthetic data. Furthermore, the shooting parameters of the synthesized blurry video, e.g., exposure time and frame-rate play significant roles in improving the performance of deblurring models. Impressively, the models trained on the blurry data synthesized by the proposed RAW-Blur pipeline can obtain more than 5dB PSNR gain against those trained on the existing synthetic blur datasets. We believe the novel realistic synthesis pipeline and the corresponding RAW video dataset can help the community to easily construct customized blur datasets to improve real-world video deblurring performance largely, instead of laboriously collecting real data pairs.

Yifan Zhan, Zhuoxiao Li, Muyao Niu et al.

We introduce KFD-NeRF, a novel dynamic neural radiance field integrated with an efficient and high-quality motion reconstruction framework based on Kalman filtering. Our key idea is to model the dynamic radiance field as a dynamic system whose temporally varying states are estimated based on two sources of knowledge: observations and predictions. We introduce a novel plug-in Kalman filter guided deformation field that enables accurate deformation estimation from scene observations and predictions. We use a shallow Multi-Layer Perceptron (MLP) for observations and model the motion as locally linear to calculate predictions with motion equations. To further enhance the performance of the observation MLP, we introduce regularization in the canonical space to facilitate the network's ability to learn warping for different frames. Additionally, we employ an efficient tri-plane representation for encoding the canonical space, which has been experimentally demonstrated to converge quickly with high quality. This enables us to use a shallower observation MLP, consisting of just two layers in our implementation. We conduct experiments on synthetic and real data and compare with past dynamic NeRF methods. Our KFD-NeRF demonstrates similar or even superior rendering performance within comparable computational time and achieves state-of-the-art view synthesis performance with thorough training.

Zhuoxiao Li, Zhihang Zhong, Shohei Nobuhara et al.

Polarization is a fundamental property of light that encodes abundant information regarding surface shape, material, illumination and viewing geometry. The computer vision community has witnessed a blossom of polarization-based vision applications, such as reflection removal, shape-from-polarization, transparent object segmentation and color constancy, partially due to the emergence of single-chip mono/color polarization sensors that make polarization data acquisition easier than ever. However, is polarization-based vision vulnerable to adversarial attacks? If so, is that possible to realize these adversarial attacks in the physical world, without being perceived by human eyes? In this paper, we warn the community of the vulnerability of polarization-based vision, which can be more serious than RGB-based vision. By adapting a commercial LCD projector, we achieve locally controllable polarizing projection, which is successfully utilized to fool state-of-the-art polarization-based vision algorithms for glass segmentation and color constancy. Compared with existing physical attacks on RGB-based vision, which always suffer from the trade-off between attack efficacy and eye conceivability, the adversarial attackers based on polarizing projection are contact-free and visually imperceptible, since naked human eyes can rarely perceive the difference of viciously manipulated polarizing light and ordinary illumination. This poses unprecedented risks on polarization-based vision, both in the monochromatic and trichromatic domain, for which due attentions should be paid and counter measures be considered.

Yuchen Yang, Yuqing Shao, Duxiu Huang et al.

Sports have long attracted broad attention as they push the limits of human physical and cognitive capabilities. Amid growing interest in spatial intelligence for vision-language models (VLMs), sports provide a natural testbed for understanding high-intensity human motion and dynamic object interactions. To this end, we present CourtSI, the first large-scale spatial intelligence dataset tailored to sports scenarios. CourtSI contains over 1M QA pairs, organized under a holistic taxonomy that systematically covers spatial counting, distance measurement, localization, and relational reasoning, across representative net sports including badminton, tennis, and table tennis. Leveraging well-defined court geometry as metric anchors, we develop a semi-automatic data engine to reconstruct sports scenes, enabling scalable curation of CourtSI. In addition, we introduce CourtSI-Bench, a high-quality evaluation benchmark comprising 3,686 QA pairs with rigorous human verification. We evaluate 25 proprietary and open-source VLMs on CourtSI-Bench, revealing a remaining human-AI performance gap and limited generalization from existing spatial intelligence benchmarks. These findings indicate that sports scenarios expose limitations in spatial intelligence capabilities captured by existing benchmarks. Further, fine-tuning Qwen3-VL-8B on CourtSI improves accuracy on CourtSI-Bench by 23.5 percentage points. The adapted model also generalizes effectively to CourtSI-Ext, an evaluation set built on a similar but unseen sport, and demonstrates enhanced spatial-aware commentary generation. Together, these findings demonstrate that CourtSI provides a scalable pathway toward advancing spatial intelligence of VLMs in sports.

Jiarui Guo, Haojia Wei, Yiming Zhang et al.

Virtual photography asks an agent to enter a prepared 3D scene with no preselected camera pose or reference image, infer a suitable shot from scene information and a language intent, choose executable camera parameters, and render the final photograph. Recent progress in vision-language models makes this kind of spatial agent increasingly plausible, but the task stresses two capabilities that remain hard to evaluate together: complex 3D spatial understanding and abstract aesthetic judgment. We introduce PhotoFlow, a Director-Reviewer-Reflector agent for closed-loop camera search. The Director builds a soft photographic blueprint and proposes diverse candidate cameras; the Reviewer combines rule checks, visual critique, and pairwise incumbent selection; and the Reflector converts failures into region memory, dead-zone suppression, and high-explore relocation. We also introduce VPhotoBench, a benchmark of 47 open-license Blender scenes and 141 language-conditioned photography missions spanning subject placement, relational composition, and atmosphere/style. On held-out experiments, PhotoFlow achieves the strongest external quality-alignment composite and success rate among one-shot prediction, single-chain reflection, anchor-bank selection, and random search under a six-round rendering budget. To our knowledge, this is the first work to make language-conditioned virtual photography in arbitrary Blender scenes an executable agent task, and our results show that an LLM-centered spatial agent can already produce strong photographs in a setting designed to challenge both 3D reasoning and aesthetic choice.

Changyao Tian, Danni Yang, Guanzhou Chen et al.

Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities.

Xiaolong Zhou, Yifei Liu, Ziyang Gong et al.

Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world deployment, such as motion blur, low light, adverse weather, lens distortion, and compression artifacts. This raises a fundamental question: how robust is the spatial intelligence of current MLLMs when visual observations are imperfect? To answer this question, we introduce SpaceDG, the first large-scale dataset for degradation-aware spatial understanding. It is constructed with a physically grounded degradation synthesis engine that embeds degradation formation process into 3D Gaussian Splatting (3DGS) rendering, enabling realistic simulation of nine degradation types. The resulting dataset contains approximately 1M QA pairs from nearly 1,000 indoor scenes. We further introduce SpaceDG-Bench, an human-verified benchmark with 1,102 questions spanning 11 reasoning categories and 9 visual degradation types, yielding over 10K VQA instances. Evaluating 25 open- and closed-source MLLMs reveals that visual degradations consistently and substantially impair spatial reasoning, exposing a critical robustness gap. Finally, we show that finetuning on SpaceDG markedly improves degradation robustness and can even surpass human performance under degraded conditions without any performance drop on clean images, highlighting the promise of degradation-aware training for robust spatial intelligence.

Yifei Liu, Zhihang Zhong, Yifan Zhan et al.

While 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and real-time rendering, the high memory consumption due to the use of millions of Gaussians limits its practicality. To mitigate this issue, improvements have been made by pruning unnecessary Gaussians, either through a hand-crafted criterion or by using learned masks. However, these methods deterministically remove Gaussians based on a snapshot of the pruning moment, leading to sub-optimized reconstruction performance from a long-term perspective. To address this issue, we introduce MaskGaussian, which models Gaussians as probabilistic entities rather than permanently removing them, and utilize them according to their probability of existence. To achieve this, we propose a masked-rasterization technique that enables unused yet probabilistically existing Gaussians to receive gradients, allowing for dynamic assessment of their contribution to the evolving scene and adjustment of their probability of existence. Hence, the importance of Gaussians iteratively changes and the pruned Gaussians are selected diversely. Extensive experiments demonstrate the superiority of the proposed method in achieving better rendering quality with fewer Gaussians than previous pruning methods, pruning over 60% of Gaussians on average with only a 0.02 PSNR decline. Our code can be found at: https://github.com/kaikai23/MaskGaussian

Zhihang Zhong, Yiming Zhang, Wei Wang et al.

Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements. Given two images of a baseball, there are infinitely many possible trajectories: accelerating or decelerating, straight or curved. This often results in blurry frames as the method averages out these possibilities. Instead of forcing the network to learn this complicated time-to-location mapping implicitly, we provide the network with an explicit hint on how far the object has traveled between start and end frames, a novel approach termed "distance indexing". This method offers a clearer learning goal for models, reducing the uncertainty tied to object speeds. Moreover, even with this extra guidance, objects can still be blurry especially when they are equally far from both input frames, due to the directional ambiguity in long-range motion. To solve this, we propose an iterative reference-based estimation strategy that breaks down a long-range prediction into several short-range steps. When integrating our plug-and-play strategies into state-of-the-art learning-based models, they exhibit markedly superior perceptual quality in arbitrary time interpolations, using a uniform distance indexing map in the same format as time indexing without requiring extra computation. Furthermore, we demonstrate that if additional latency is acceptable, a continuous map estimator can be employed to compute a pixel-wise dense distance indexing using multiple nearby frames. Combined with efficient multi-frame refinement, this extension can further disambiguate complex motion, thus enhancing performance both qualitatively and quantitatively. Additionally, the ability to manually specify distance indexing allows for independent temporal manipulation of each object, providing a novel tool for video editing tasks such as re-timing.

Yuning Gong, Yifei Liu, Yifan Zhan et al.

Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fragmented, heavy, or constrained by legacy pipelines, resulting in high deployment friction and limited support for dynamic content and generative models. In this work, we present Visionary, an open, web-native platform for real-time various Gaussian Splatting and meshes rendering. Built on an efficient WebGPU renderer with per-frame ONNX inference, Visionary enables dynamic neural processing while maintaining a lightweight, "click-to-run" browser experience. It introduces a standardized Gaussian Generator contract, which not only supports standard 3DGS rendering but also allows plug-and-play algorithms to generate or update Gaussians each frame. Such inference also enables us to apply feedforward generative post-processing. The platform further offers a plug in three.js library with a concise TypeScript API for seamless integration into existing web applications. Experiments show that, under identical 3DGS assets, Visionary achieves superior rendering efficiency compared to current Web viewers due to GPU-based primitive sorting. It already supports multiple variants, including MLP-based 3DGS, 4DGS, neural avatars, and style transformation or enhancement networks. By unifying inference and rendering directly in the browser, Visionary significantly lowers the barrier to reproduction, comparison, and deployment of 3DGS-family methods, serving as a unified World Model Carrier for both reconstructive and generative paradigms.

Liyuan Deng, Shujian Deng, Yongkang Chen et al.

Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration), a tool-augmented reinforcement learning (RL) framework that teaches LLMs to complete the closed-loop CAD-CAE process. Specifically, we cast CAD generation, CAE solving, result parsing, and geometry revision as an interactive RL environment, where an LLM learns to orchestrate external tools and revise parametric geometries until constraints are satisfied. To make this learning stable and industrially usable, we design a multi-constraint reward that jointly encourages feasibility, toolchain robustness, and structured output validity. In addition, we contribute an industry-aligned dataset that covers 25 component categories with executable CAD-CAE tasks to support realistic training and evaluation. Experiments show that COSMO-Agent training substantially improves small open-source LLMs for constraint-driven design, exceeding large open-source and strong closed-source models in feasibility, efficiency, and stability.

Liyuan Deng, Shujian Deng, Yongkang Chen et al.

Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration), a tool-augmented reinforcement learning (RL) framework that teaches LLMs to complete the closed-loop CAD-CAE process. Specifically, we cast CAD generation, CAE solving, result parsing, and geometry revision as an interactive RL environment, where an LLM learns to orchestrate external tools and revise parametric geometries until constraints are satisfied. To make this learning stable and industrially usable, we design a multi-constraint reward that jointly encourages feasibility, toolchain robustness, and structured output validity. In addition, we contribute an industry-aligned dataset that covers 25 component categories with executable CAD-CAE tasks to support realistic training and evaluation. Experiments show that COSMO-Agent training substantially improves small open-source LLMs for constraint-driven design, exceeding large open-source and strong closed-source models in feasibility, efficiency, and stability.

Linfeng Dong, Yuchen Yang, Hao Wu et al.

We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first to provide large-scale, fine-grained annotations for racket pose alongside traditional ball positions, enabling research into complex human-object interactions. It is designed to tackle three interconnected tasks: fine-grained ball tracking, articulated racket pose estimation, and predictive ball trajectory forecasting. Our evaluation of established baselines reveals a critical insight for multi-modal fusion: while naively concatenating racket pose features degrades performance, a CrossAttention mechanism is essential to unlock their value, leading to trajectory prediction results that surpass strong unimodal baselines. RacketVision provides a versatile resource and a strong starting point for future research in dynamic object tracking, conditional motion forecasting, and multimodal analysis in sports. Project page at https://github.com/OrcustD/RacketVision

Mingxin Liu, Shuran Ma, Shibei Meng et al.

While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a pioneering reasoning-oriented benchmark for Text-Image-to-Video (TI2V) synthesis that shifts the evaluative focus from surface-level aesthetics to deep cognitive reasoning. RISE-Video comprises 467 meticulously human-annotated samples spanning eight rigorous categories, providing a structured testbed for probing model intelligence across diverse dimensions, ranging from commonsense and spatial dynamics to specialized subject domains. Our framework introduces a multi-dimensional evaluation protocol consisting of four metrics: \textit{Reasoning Alignment}, \textit{Temporal Consistency}, \textit{Physical Rationality}, and \textit{Visual Quality}. To further support scalable evaluation, we propose an automated pipeline leveraging Large Multimodal Models (LMMs) to emulate human-centric assessment. Extensive experiments on 11 state-of-the-art TI2V models reveal pervasive deficiencies in simulating complex scenarios under implicit constraints, offering critical insights for the advancement of future world-simulating generative models.

Jiaqi Chen, Xinhao Ji, Yuanyuan Gao et al.

Neural scene representations, such as 3D Gaussian Splatting (3DGS), have enabled high-quality neural rendering; however, their large storage and transmission costs hinder deployment in resource-constrained environments. Existing compression methods either rely on costly optimization, which is slow and scene-specific, or adopt training-free pruning and quantization, which degrade rendering quality under high compression ratios. In contrast, recent data-driven approaches provide a promising direction to overcome this trade-off, enabling efficient compression while preserving high rendering quality. We introduce ExGS, a novel feed-forward framework that unifies Universal Gaussian Compression (UGC) with GaussPainter for Extreme 3DGS compression. UGC performs re-optimization-free pruning to aggressively reduce Gaussian primitives while retaining only essential information, whereas GaussPainter leverages powerful diffusion priors with mask-guided refinement to restore high-quality renderings from heavily pruned Gaussian scenes. Unlike conventional inpainting, GaussPainter not only fills in missing regions but also enhances visible pixels, yielding substantial improvements in degraded renderings. To ensure practicality, it adopts a lightweight VAE and a one-step diffusion design, enabling real-time restoration. Our framework can even achieve over 100X compression (reducing a typical 354.77 MB model to about 3.31 MB) while preserving fidelity and significantly improving image quality under challenging conditions. These results highlight the central role of diffusion priors in bridging the gap between extreme compression and high-quality neural rendering. Our code repository will be released at: https://github.com/chenttt2001/ExGS

Yuchen Yang, Linfeng Dong, Wei Wang et al.

In 3D human pose and shape estimation, SMPLify remains a robust baseline that solves inverse kinematics (IK) through iterative optimization. However, its high computational cost limits its practicality. Recent advances across domains have shown that replacing iterative optimization with data-driven neural networks can achieve significant runtime improvements without sacrificing accuracy. Motivated by this trend, we propose Learnable SMPLify, a neural framework that replaces the iterative fitting process in SMPLify with a single-pass regression model. The design of our framework targets two core challenges in neural IK: data construction and generalization. To enable effective training, we propose a temporal sampling strategy that constructs initialization-target pairs from sequential frames. To improve generalization across diverse motions and unseen poses, we propose a human-centric normalization scheme and residual learning to narrow the solution space. Learnable SMPLify supports both sequential inference and plug-in post-processing to refine existing image-based estimators. Extensive experiments demonstrate that our method establishes itself as a practical and simple baseline: it achieves nearly 200x faster runtime compared to SMPLify, generalizes well to unseen 3DPW and RICH, and operates in a model-agnostic manner when used as a plug-in tool on LucidAction. The code is available at https://github.com/Charrrrrlie/Learnable-SMPLify.

Yue Zhou, Zhihang Zhong, Xue Yang

Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding. However, most methods rely on training with general image datasets, and the lack of geospatial data leads to poor performance on earth observation. Numerous geospatial image-text pair datasets and VLFMs fine-tuned on them have been proposed recently. These new approaches aim to leverage large-scale, multimodal geospatial data to build versatile intelligent models with diverse geo-perceptive capabilities, which we refer to as Vision-Language Geo-Foundation Models (VLGFMs). This paper thoroughly reviews VLGFMs, summarizing and analyzing recent developments in the field. In particular, we introduce the background and motivation behind the rise of VLGFMs, highlighting their unique research significance. Then, we systematically summarize the core technologies employed in VLGFMs, including data construction, model architectures, and applications of various multimodal geospatial tasks. Finally, we conclude with insights, issues, and discussions regarding future research directions. To the best of our knowledge, this is the first comprehensive literature review of VLGFMs. We keep tracing related works at https://github.com/zytx121/Awesome-VLGFM.

Yuchen Yang, Xuanyi Liu, Xing Gao et al.

Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlooking the inherent depth ambiguity issue. Due to the information loss in 3D-to-2D projection, multiple potential depths may exist, yet only some of them are plausible in human structure. To tackle depth ambiguity, we propose a novel unsupervised framework featuring a multi-hypothesis detector and multiple tailored pretext tasks. The detector extracts multiple hypotheses from a heatmap within a local window, effectively managing the multi-solution problem. Furthermore, the pretext tasks harness 3D human priors from the SMPL model to regularize the solution space of pose estimation, aligning it with the empirical distribution of 3D human structures. This regularization is partially achieved through a GCN-based discriminator within the discriminative learning, and is further complemented with synthetic images through rendering, ensuring plausible estimations. Consequently, our approach demonstrates state-of-the-art unsupervised 3D pose estimation performance on various human datasets. Further evaluations on data scale-up and one animal dataset highlight its generalization capabilities. Code will be available at https://github.com/Charrrrrlie/X-as-Supervision.

Zhihang Zhong, Ye Gao, Yinqiang Zheng et al.

Real-world video deblurring in real time still remains a challenging task due to the complexity of spatially and temporally varying blur itself and the requirement of low computational cost. To improve the network efficiency, we adopt residual dense blocks into RNN cells, so as to efficiently extract the spatial features of the current frame. Furthermore, a global spatio-temporal attention module is proposed to fuse the effective hierarchical features from past and future frames to help better deblur the current frame. Another issue that needs to be addressed urgently is the lack of a real-world benchmark dataset. Thus, we contribute a novel dataset (BSD) to the community, by collecting paired blurry/sharp video clips using a co-axis beam splitter acquisition system. Experimental results show that the proposed method (ESTRNN) can achieve better deblurring performance both quantitatively and qualitatively with less computational cost against state-of-the-art video deblurring methods. In addition, cross-validation experiments between datasets illustrate the high generality of BSD over the synthetic datasets. The code and dataset are released at https://github.com/zzh-tech/ESTRNN.

Zhihang Zhong, Yinqiang Zheng, Imari Sato

Joint rolling shutter correction and deblurring (RSCD) techniques are critical for the prevalent CMOS cameras. However, current approaches are still based on conventional energy optimization and are developed for static scenes. To enable learning-based approaches to address real-world RSCD problem, we contribute the first dataset, BS-RSCD, which includes both ego-motion and object-motion in dynamic scenes. Real distorted and blurry videos with corresponding ground truth are recorded simultaneously via a beam-splitter-based acquisition system. Since direct application of existing individual rolling shutter correction (RSC) or global shutter deblurring (GSD) methods on RSCD leads to undesirable results due to inherent flaws in the network architecture, we further present the first learning-based model (JCD) for RSCD. The key idea is that we adopt bi-directional warping streams for displacement compensation, while also preserving the non-warped deblurring stream for details restoration. The experimental results demonstrate that JCD achieves state-of-the-art performance on the realistic RSCD dataset (BS-RSCD) and the synthetic RSC dataset (Fastec-RS). The dataset and code are available at https://github.com/zzh-tech/RSCD.

Yangfu Li, Yuning Gong, Hongjian Zhan et al.

Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce geometric priors from visual experts as additional supervision. However, we observe that such supervision is typically suboptimal: it is biased toward geometric precision and offers limited reasoning utility. To bridge this gap, we propose Perceptual Flow Network (PFlowNet), which eschews rigid alignment with the expert priors and achieves interpretable yet more effective visual reasoning. Specifically, PFlowNet decouples perception from reasoning to establish a self-conditioned generation process. Based on this, it integrates multi-dimensional rewards with vicinal geometric shaping via variational reinforcement learning, thereby facilitating reasoning-oriented perceptual behaviors while preserving visual reliability. PFlowNet delivers a provable performance guarantee and competitive empirical results, particularly setting new SOTA records on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).

Yutong Chen, Yifan Zhan, Zhihang Zhong et al.

Neural rendering techniques have significantly advanced 3D human body modeling. However, previous approaches often overlook dynamics induced by factors such as motion inertia, leading to challenges in scenarios like abrupt stops after rotation, where the pose remains static while the appearance changes. This limitation arises from reliance on a single pose as conditional input, resulting in ambiguity in mapping one pose to multiple appearances. In this study, we elucidate that variations in human appearance depend not only on the current frame's pose condition but also on past pose states. Therefore, we introduce Dyco, a novel method utilizing the delta pose sequence representation for non-rigid deformations and canonical space to effectively model temporal appearance variations. To prevent a decrease in the model's generalization ability to novel poses, we further propose low-dimensional global context to reduce unnecessary inter-body part dependencies and a quantization operation to mitigate overfitting of the delta pose sequence by the model. To validate the effectiveness of our approach, we collected a novel dataset named I3D-Human, with a focus on capturing temporal changes in clothing appearance under approximate poses. Through extensive experiments on both I3D-Human and existing datasets, our approach demonstrates superior qualitative and quantitative performance. In addition, our inertia-aware 3D human method can unprecedentedly simulate appearance changes caused by inertia at different velocities.

Yuanyuan Gao, Hao Li, Jiaqi Chen et al.

Despite its significant achievements in large-scale scene reconstruction, 3D Gaussian Splatting still faces substantial challenges, including slow processing, high computational costs, and limited geometric accuracy. These core issues arise from its inherently unstructured design and the absence of efficient parallelization. To overcome these challenges simultaneously, we introduce CityGS-X, a scalable architecture built on a novel parallelized hybrid hierarchical 3D representation (PH^2-3D). As an early attempt, CityGS-X abandons the cumbersome merge-and-partition process and instead adopts a newly-designed batch-level multi-task rendering process. This architecture enables efficient multi-GPU rendering through dynamic Level-of-Detail voxel allocations, significantly improving scalability and performance. Through extensive experiments, CityGS-X consistently outperforms existing methods in terms of faster training times, larger rendering capacities, and more accurate geometric details in large-scale scenes. Notably, CityGS-X can train and render a scene with 5,000+ images in just 5 hours using only 4 * 4090 GPUs, a task that would make other alternative methods encounter Out-Of-Memory (OOM) issues and fail completely. This implies that CityGS-X is far beyond the capacity of other existing methods.

Yuchen Yang, Wei Wang, Yifei Liu et al.

Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, which hinder the evaluation of state-of-the-art algorithms. To address these limitations, we introduce SGA-INTERACT, the first 3D skeleton-based benchmark for group activity understanding. It features complex activities inspired by basketball tactics, emphasizing rich spatial interactions and long-term dependencies. SGA-INTERACT introduces Temporal Group Activity Localization (TGAL) task, extending group activity understanding to untrimmed sequences, filling the gap left by GAR as a standalone task. In addition to the benchmark, we propose One2Many, a novel framework that employs a pretrained 3D skeleton backbone for unified individual feature extraction. This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks. We conduct extensive evaluations on SGA-INTERACT using two skeleton-based methods, three RGB-based methods, and a proposed baseline within the One2Many framework. The general low performance of baselines highlights the benchmark's challenges, motivating advancements in group activity understanding.

Muyao Niu, Yifan Zhan, Qingtian Zhu et al.

The development of 3D human avatars from multi-view videos represents a significant yet challenging task in the field. Recent advancements, including 3D Gaussian Splattings (3DGS), have markedly progressed this domain. Nonetheless, existing techniques necessitate the use of high-quality sharp images, which are often impractical to obtain in real-world settings due to variations in human motion speed and intensity. In this study, we attempt to explore deriving sharp intrinsic 3D human Gaussian avatars from blurry video footage in an end-to-end manner. Our approach encompasses a 3D-aware, physics-oriented model of blur formation attributable to human movement, coupled with a 3D human motion model to clarify ambiguities found in motion-induced blurry images. This methodology facilitates the concurrent learning of avatar model parameters and the refinement of sub-frame motion parameters from a coarse initialization. We have established benchmarks for this task through a synthetic dataset derived from existing multi-view captures, alongside a real-captured dataset acquired through a 360-degree synchronous hybrid-exposure camera system. Comprehensive evaluations demonstrate that our model surpasses existing baselines.

Yuanyuan Gao, Hao Li, Yifei Liu et al.

The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets. In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs. Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks. Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance.

Yiming Zhang, Zhe Wang, Xinjie Li et al.

Human body restoration plays a vital role in various applications related to the human body. Despite recent advances in general image restoration using generative models, their performance in human body restoration remains mediocre, often resulting in foreground and background blending, over-smoothing surface textures, missing accessories, and distorted limbs. Addressing these challenges, we propose a novel approach by constructing a human body-aware diffusion model that leverages domain-specific knowledge to enhance performance. Specifically, we employ a pretrained body attention module to guide the diffusion model's focus on the foreground, addressing issues caused by blending between the subject and background. We also demonstrate the value of revisiting the language modality of the diffusion model in restoration tasks by seamlessly incorporating text prompt to improve the quality of surface texture and additional clothing and accessories details. Additionally, we introduce a diffusion sampler tailored for fine-grained human body parts, utilizing local semantic information to rectify limb distortions. Lastly, we collect a comprehensive dataset for benchmarking and advancing the field of human body restoration. Extensive experimental validation showcases the superiority of our approach, both quantitatively and qualitatively, over existing methods.

Yifan Zhan, Wangze Xu, Qingtian Zhu et al.

We present R3-Avatar, incorporating a temporal codebook, to overcome the inability of human avatars to be both animatable and of high-fidelity rendering quality. Existing video-based reconstruction of 3D human avatars either focuses solely on rendering, lacking animation support, or learns a pose-appearance mapping for animating, which degrades under limited training poses or complex clothing. In this paper, we adopt a "record-retrieve-reconstruct" strategy that ensures high-quality rendering from novel views while mitigating degradation in novel poses. Specifically, disambiguating timestamps record temporal appearance variations in a codebook, ensuring high-fidelity novel-view rendering, while novel poses retrieve corresponding timestamps by matching the most similar training poses for augmented appearance. Our R3-Avatar outperforms cutting-edge video-based human avatar reconstruction, particularly in overcoming visual quality degradation in extreme scenarios with limited training human poses and complex clothing.

Hao Wu, Zhihang Zhong, Xiao Sun

Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches have garnered increasing attention. However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on raw captions or parsed objects, which fail to capture the full semantic richness of the data. In this paper, we propose Dive Into Retrieval (DIR), a method designed to enhance both the image-to-text retrieval process and the utilization of retrieved text to achieve a more comprehensive understanding of the visual content. Our approach introduces two key innovations: (1) diffusion-guided retrieval enhancement, where a pretrained diffusion model guides image feature learning by reconstructing noisy images, allowing the model to capture more comprehensive and fine-grained visual information beyond standard annotated captions; and (2) a high-quality retrieval database, which provides comprehensive semantic information to enhance caption generation, especially in out-of-domain scenarios. Extensive experiments demonstrate that DIR not only maintains competitive in-domain performance but also significantly improves out-of-domain generalization, all without increasing inference costs.

Wangze Xu, Yifan Zhan, Zhihang Zhong et al.

The emergence of neural rendering has significantly advanced the rendering quality of 3D human avatars, with the recently popular 3DGS technique enabling real-time performance. However, SMPL-driven 3DGS human avatars still struggle to capture fine appearance details due to the complex mapping from pose to appearance during fitting. In this paper, we propose SeqAvatar, which excavates the explicit 3DGS representation to better model human avatars based on a hierarchical motion context. Specifically, we utilize a coarse-to-fine motion conditions that incorporate both the overall human skeleton and fine-grained vertex motions for non-rigid deformation. To enhance the robustness of the proposed motion conditions, we adopt a spatio-temporal multi-scale sampling strategy to hierarchically integrate more motion clues to model human avatars. Extensive experiments demonstrate that our method significantly outperforms 3DGS-based approaches and renders human avatars orders of magnitude faster than the latest NeRF-based models that incorporate temporal context, all while delivering performance that is at least comparable or even superior. Project page: https://zezeaaa.github.io/projects/SeqAvatar/

Yuanyuan Gao, Yuning Gong, Yifei Liu et al.

3D Gaussian Splatting (3DGS) has emerged as an efficient approach for achieving photorealistic rendering. Recent MLP-based variants further improve visual fidelity but introduce substantial decoding overhead during rendering. To alleviate computation cost, several pruning strategies and level-of-detail (LOD) techniques have been introduced, aiming to effectively reduce the number of Gaussian primitives in large-scale scenes. However, our analysis reveals that significant redundancy still remains due to the lack of occlusion awareness. In this work, we propose Proxy-GS, a novel pipeline that exploits a proxy to introduce Gaussian occlusion awareness from any view. At the core of our approach is a fast proxy system capable of producing precise occlusion depth maps at a resolution of 1000x1000 under 1ms. This proxy serves two roles: first, it guides the culling of anchors and Gaussians to accelerate rendering speed. Second, it guides the densification towards surfaces during training, avoiding inconsistencies in occluded regions, and improving the rendering quality. In heavily occluded scenarios, such as the MatrixCity Streets dataset, Proxy-GS not only equips MLP-based Gaussian splatting with stronger rendering capability but also achieves faster rendering speed. Specifically, it achieves more than 2.5x speedup over Octree-GS, and consistently delivers substantially higher rendering quality. Code will be public upon acceptance.