arXiv subjects

Zhenghao Chen

Publications and source records attributed to Zhenghao Chen.

At least 19 recordsLinked to original sources

arXiv2026

M$^3$ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression

High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment remains constrained by representation size, dynamic updates, and computational cost. Existing multi-view video benchmarks provide valuable real-captured content, but they make it difficult to isolate the effects of controlled camera geometry, representation efficiency, and temporal redundancy. We introduce M$^3$ISR, a controlled synthetic benchmark for 3D and 4D Gaussian Splatting (3DGS/4DGS). The benchmark contains 25 scenes from five indoor and outdoor scene groups, two camera/motion configurations, six synchronized 1080p views, and dense ground-truth annotations including RGB, camera parameters, depth, semantic and instance segmentation, and static--dynamic masks. The shared-center camera design intentionally isolates angular view variation and enables controlled evaluation of novel-view synthesis and representation efficiency. We organize M$^3$ISR into five complementary tracks covering 3DGS synthesis, 4DGS synthesis, 4DGS streaming, 3DGS compression, and 4DGS compression. Representative baseline results show small differences in static reconstruction quality but substantial differences in representation storage, while the evaluated streaming methods exhibit substantially higher reported training or reconstruction cost than the corresponding offline dynamic reconstruction baselines. We further define feedforward compression tasks for 3DGS and 4DGS and provide reference rate--distortion formulations and preliminary baseline evaluations. The benchmark is intended as a controlled and complementary testbed for systematic study of Gaussian-based FVV reconstruction, compression, and streaming.

cs.CV↗

arXiv2026

Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization

Recent video representation methods that rely on fixed-grid, patch-wise tokenization often exhibit limited versatility.Spatially, uniformly allocating a fixed number of tokens often leads to over-encoding in low-information regions. Temporally, reducing redundancy remains challenging without explicitly distinguishing between static and dynamic content. In this work, we introduce the Gaussian Video Transformer (GVT), a versatile video representation framework built on a feed-forward 2D Gaussian Splatting (2DGS) tokenization scheme. We first extract latent rigid features from a video clip and represent them with a set of 2D Gaussians generated by our proposed Spatio-Temporal Gaussian Embedding (STGE) mechanism in a feed-forward manner. Such 2D Gaussians not only enhance spatial adaptability by assigning higher (resp., lower) rendering weights to regions with higher (resp., lower) information content during rasterization, but also improve generalization by avoiding per-video optimization. To enhance the temporal versatility, we introduce a Gaussian Set Partitioning (GSP) strategy that separates the 2D Gaussians into static and dynamic sets, which explicitly model static content shared across different time-steps and dynamic content specific to each time-step, enabling a compact representation. We evaluate GVT across four tasks: video reconstruction, video action recognition, video compression, and video generation, on the UCF101, Kinetics, and DAVIS datasets. The results demonstrate state-of-the-art reconstruction and compression performance, improved action recognition, and video generation performance comparable to the baseline MAGVIT-v2.

cs.CV↗

arXiv2026

Seeing What Matters: Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Report Generation

Despite rapid advances in chest X-ray (CXR) foundation models, most radiology report generation (RRG) systems still rely on heavily downsampled inputs (e.g., 256x256) due to the fixed visual token budgets of pretrained vision encoders, suppressing subtle yet clinically important cues present in native-resolution images. However, enabling high-resolution (high-res) perception remains challenging: naive tiling causes prohibitive token inflation, while global compression suppresses subtle lesions and degrades diagnostic fidelity. Inspired by radiologists' workflow, localizing suspicious regions before detailed high-res assessment. We propose Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Reporting (LePaX), the first RRG framework that enables efficient high-res CXR perception (up to 1920x1920) without increasing the vision-token count. LePaX formulates high-res perception as a constrained spatial resolution allocation problem under a fixed token budget and introduces two key components: Learnable Spatial Resolution Allocation (LSRA), which learns a spatial utility map that adaptively allocates limited high-res capacity to diagnostically relevant regions, enabling targeted extraction of high-res patches from native CXRs; and Global-Regional Fusion (GRF), which performs token-preserving region-to-global refinement by projecting high-resolution regional evidence back onto the global feature grid through spatially aligned resolution write-back, avoiding token inflation. Experiments on multiple CXR benchmarks demonstrate that LePaX consistently improves both clinical and linguistic metrics while enabling native-resolution CXR perception with over 10x fewer visual tokens than naive high-res tiling.

cs.CV↗

arXiv2026

Neural Stereo Video Compression with Hybrid Disparity Compensation

Disparity compensation represents the primary strategy in stereo video compression (SVC) for exploiting cross-view redundancy. These mechanisms can be broadly categorized into two types: one that employs explicit horizontal shifting, and another that utilizes an implicit cross-attention mechanism to reduce cross-view disparity redundancy. In this work, we propose a hybrid disparity compensation (HDC) strategy that leverages explicit pixel displacement as a robust prior feature to simplify optimization and perform implicit cross-attention mechanisms for subsequent warping operations, thereby capturing a broader range of disparity information. Specifically, HDC first computes a similarity map by fusing the horizontally shifted cross-view features to capture pixel displacement information. This similarity map is then normalized into an "explicit pixel-wise attention score" to perform the cross-attention mechanism, implicitly aligning features from one view to another. Building upon HDC, we introduce a novel end-to-end optimized neural stereo video compression framework, which integrates HDC-based modules into key coding operations, including cross-view feature extraction and reconstruction (HDC-FER) and cross-view entropy modeling (HDC-EM). Extensive experiments on SVC benchmarks, including KITTI 2012, KITTI 2015, and Nagoya, which cover both autonomous driving and general scenes, demonstrate that our framework outperforms both neural and traditional SVC methodologies.

cs.CV↗

arXiv2026

Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting

The development of Time-Series Forecasting (TSF) models is often constrained by the lack of comprehensive datasets, especially in Global Station Weather Forecasting (GSWF), where existing datasets are small, temporally short, and spatially sparse. To address this, we introduce WEATHER-5K, a large-scale observational weather dataset that better reflects real-world conditions, supporting improved model training and evaluation. While recent TSF methods perform well on benchmarks, they lag behind operational Numerical Weather Prediction systems in capturing complex weather dynamics and extreme events. We propose PhysicsFormer, a physics-informed forecasting model combining a dynamic core with a Transformer residual to predict future weather states. Physical consistency is enforced via pressure-wind alignment and energy-aware smoothness losses, ensuring plausible dynamics while capturing complex temporal patterns. We benchmark PhysicsFormer and other TSF models against operational systems across several weather variables, extreme event prediction, and model complexity, providing a comprehensive assessment of the gap between academic TSF models and operational forecasting. The dataset and benchmark implementation are available at: https://github.com/taohan10200/WEATHER-5K.

cs.LG↗

arXiv2026

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs

Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reasoning by introducing 3D priors or geometric supervision, which enhances performance but incurs substantial data preparation and alignment costs. In contrast, purely 2D approaches often struggle with multi-frame spatial reasoning due to their limited ability to capture cross-frame spatial relationships. To address these limitations, we propose EgoMind, a Chain-of-Thought framework that enables geometry-free spatial reasoning through Role-Play Caption, which jointly constructs a coherent linguistic scene graph across frames, and Progressive Spatial Analysis, which progressively reasons toward task-specific questions. With only 5K auto-generated SFT samples and 20K RL samples, EgoMind achieves competitive results on VSI-Bench, SPAR-Bench, SITE-Bench, and SPBench, demonstrating its effectiveness in strengthening the spatial reasoning capabilities of MLLMs and highlighting the potential of linguistic reasoning for spatial cognition. Code and data are released at https://github.com/Hyggge/EgoMind.

cs.CV↗

arXiv2026

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression

The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack a principled mechanism for joint rate-distortion (RD) optimization due to the disconnect between representation learning and entropy modeling. We propose RDVQ, a unified framework that enables end-to-end RD optimization for VQ-based compression via a differentiable relaxation of the codebook distribution, allowing the entropy loss to directly shape the latent prior. We further develop an autoregressive entropy model that supports accurate entropy modeling and test-time rate control. Extensive experiments demonstrate that RDVQ achieves strong performance at extremely low bitrates with a lightweight architecture, attaining competitive or superior perceptual quality with significantly fewer parameters. Compared with RDEIC, RDVQ reduces bitrate by up to 75.71% on DISTS and 37.63% on LPIPS on DIV2K-val. Beyond empirical gains, RDVQ introduces an entropy-constrained formulation of VQ, highlighting the potential for a more unified view of image tokenization and compression. The code will be available at https://github.com/CVL-UESTC/RDVQ.

cs.CV↗

arXiv2026

Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation

The growing complexity of visuomotor policies poses significant challenges for deployment with heterogeneous robotic hardware constraints. However, most existing model-efficient approaches for robotic manipulation are device- and model-specific, lack generalizability, and require time-consuming per-device optimization during the adaptation process. In this work, we propose a unified framework named \textbf{D}evice-\textbf{C}onditioned \textbf{Q}uantization-\textbf{F}or-\textbf{A}ll (DC-QFA) which amortizes deployment effort with the device-conditioned quantization-aware training and hardware-constrained architecture search. Specifically, we introduce a single supernet that spans a rich design space over network architectures and mixed-precision bit-widths. It is optimized with latency- and memory-aware regularization, guided by per-device lookup tables. With this supernet, for each target platform, we can perform a once-for-all lightweight search to select an optimal subnet without any per-device re-optimization, which enables more generalizable deployment across heterogeneous hardware, and substantially reduces deployment time. To improve long-horizon stability under low precision, we further introduce multi-step on-policy distillation to mitigate error accumulation during closed-loop execution. Extensive experiments on three representative policy backbones, such as DiffusionPolicy-T, MDT-V, and OpenVLA-OFT, demonstrate that our DC-QFA achieves $2\text{-}3\times$ acceleration on edge devices, consumer-grade GPUs, and cloud platforms, with negligible performance drop in task success. Real-world evaluations on an Inovo robot equipped with a force/torque sensor further validates that our low-bit DC-QFA policies maintain stable, contact-rich manipulation even under severe quantization.

cs.RO↗

arXiv2026

Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting

While AI-based numerical weather prediction (NWP) enables rapid forecasting, generating high-resolution outputs remains computationally demanding due to limited multi-scale adaptability and inefficient data representations. We propose the 3D Gaussian splatting-based scale-aware vision transformer (GSSA-ViT), a novel framework for arbitrary-resolution forecasting and flexible downscaling of high-dimensional atmospheric fields. Specifically, latitude-longitude grid points are treated as centers of 3D Gaussians. A generative 3D Gaussian prediction scheme is introduced to estimate key parameters, including covariance, attributes, and opacity, for unseen samples, improving generalization and mitigating overfitting. In addition, a scale-aware attention module is designed to capture cross-scale dependencies, enabling the model to effectively integrate information across varying downscaling ratios and support continuous resolution adaptation. To our knowledge, this is the first NWP approach that combines generative 3D Gaussian modeling with scale-aware attention for unified multi-scale prediction. Experiments on ERA5 show that the proposed method accurately forecasts 87 atmospheric variables at arbitrary resolutions, while evaluations on ERA5 and CMIP6 demonstrate its superior performance in downscaling tasks. The proposed framework provides an efficient and scalable solution for high-resolution, multi-scale atmospheric prediction and downscaling. Code is available at: https://github.com/binbin2xs/weather-GS.

cs.CV↗

arXiv2026

Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV

Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and background, recognizing actions in such samples remains challenging because of the background distractions. Receptance Weighted Key Value (RWKV), which learns interaction between various dimensions, shows promise for global modeling. While directly applying RWKV to wide-angle FSAR may fail to highlight subjects due to excessive background information. Additionally, temporal relation degraded by frames with similar backgrounds is difficult to reconstruct, further impacting performance. Therefore, we design the CompOund SegmenTation and Temporal REconstructing RWKV (Otter). Specifically, the Compound Segmentation Module~(CSM) is devised to segment and emphasize key patches in each frame, effectively highlighting subjects against background information. The Temporal Reconstruction Module (TRM) is incorporated into the temporal-enhanced prototype construction to enable bidirectional scanning, allowing better reconstruct temporal relation. Furthermore, a regular prototype is combined with the temporal-enhanced prototype to simultaneously enhance subject emphasis and temporal modeling, improving wide-angle FSAR performance. Extensive experiments on benchmarks such as SSv2, Kinetics, UCF101, and HMDB51 demonstrate that Otter achieves state-of-the-art performance. Extra evaluation on the VideoBadminton dataset further validates the superiority of Otter in wide-angle FSAR.

cs.CV↗

arXiv2026

Generative Video Compression with One-Dimensional Latent Representation

Recent advancements in generative video codec (GVC) typically encode video into a 2D latent grid and employ high-capacity generative decoders for reconstruction. However, this paradigm still leaves two key challenges in fully exploiting spatial-temporal redundancy: Spatially, the 2D latent grid inevitably preserves intra-frame redundancy due to its rigid structure, where adjacent patches remain highly similar, thereby necessitating a higher bitrate. Temporally, the 2D latent grid is less effective for modeling long-term correlations in a compact and semantically coherent manner, as it hinders the aggregation of common contents across frames. To address these limitations, we introduce Generative Video Compression with One-Dimensional (1D) Latent Representation (GVC1D). GVC1D encodes the video data into extreme compact 1D latent tokens conditioned on both short- and long-term contexts. Without the rigid 2D spatial correspondence, these 1D latent tokens can adaptively attend to semantic regions and naturally facilitate token reduction, thereby reducing spatial redundancy. Furthermore, the proposed 1D memory provides semantically rich long-term context while maintaining low computational cost, thereby further reducing temporal redundancy. Experimental results indicate that GVC1D attains superior compression efficiency, where it achieves bitrate reductions of 60.4\% under LPIPS and 68.8\% under DISTS on the HEVC Class B dataset, surpassing the previous video compression methods.Project: https://gvc1d.github.io/

cs.CV↗

arXiv2026

LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction

Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While recent 3D Gaussian Splatting (3DGS) has advanced FVV due to its superior rendering speed, Streaming Free-Viewpoint Video (SFVV) introduces additional demands for rapid optimization, high-fidelity reconstruction under sparse constraints, and minimal storage footprints. To bridge this gap, we propose StreamLoD-GS, an LoD-based Gaussian Splatting framework designed specifically for SFVV. Our approach integrates three core innovations: 1) an Anchor- and Octree-based LoD-structured 3DGS with a hierarchical Gaussian dropout technique to ensure efficient and stable optimization while maintaining high-quality rendering; 2) a GMM-based motion partitioning mechanism that separates dynamic and static content, refining dynamic regions while preserving background stability; and 3) a quantized residual refinement framework that significantly reduces storage requirements without compromising visual fidelity. Extensive experiments demonstrate that StreamLoD-GS achieves competitive or state-of-the-art performance in terms of quality, efficiency, and storage.

cs.GR↗

arXiv2025

IGDMRec: Behavior Conditioned Item Graph Diffusion for Multimodal Recommendation

Multimodal recommender systems (MRSs) are critical for various online platforms, offering users more accurate personalized recommendations by incorporating multimodal information of items. Structure-based MRSs have achieved state-of-the-art performance by constructing semantic item graphs, which explicitly model relationships between items based on modality feature similarity. However, such semantic item graphs are often noisy due to 1) inherent noise in multimodal information and 2) misalignment between item semantics and user-item co-occurrence relationships, which introduces false links and leads to suboptimal recommendations. To address this challenge, we propose Item Graph Diffusion for Multimodal Recommendation (IGDMRec), a novel method that leverages a diffusion model with classifier-free guidance to denoise the semantic item graph by integrating user behavioral information. Specifically, IGDMRec introduces a Behavior-conditioned Graph Diffusion (BGD) module, incorporating interaction data as conditioning information to guide the denoising of the semantic item graph. Additionally, a Conditional Denoising Network (CD-Net) is designed to implement the denoising process with manageable complexity. Finally, we propose a contrastive representation augmentation scheme that leverages both the denoised item graph and the original item graph to enhance item representations. \LL{Extensive experiments on four real-world datasets demonstrate the superiority of IGDMRec over competitive baselines, with robustness analysis validating its denoising capability and ablation studies verifying the effectiveness of its key components.

cs.IR↗

arXiv2025

Improving Lesion Segmentation in Medical Images by Global and Regional Feature Compensation

Automated lesion segmentation of medical images has made tremendous improvements in recent years due to deep learning advancements. However, accurately capturing fine-grained global and regional feature representations remains a challenge. Many existing methods obtain suboptimal performance on complex lesion segmentation due to information loss during typical downsampling operations and the insufficient capture of either regional or global features. To address these issues, we propose the Global and Regional Compensation Segmentation Framework (GRCSF), which introduces two key innovations: the Global Compensation Unit (GCU) and the Region Compensation Unit (RCU). The proposed GCU addresses resolution loss in the U-shaped backbone by preserving global contextual features and fine-grained details during multiscale downsampling. Meanwhile, the RCU introduces a self-supervised learning (SSL) residual map generated by Masked Autoencoders (MAE), obtained as pixel-wise differences between reconstructed and original images, to highlight regions with potential lesions. These SSL residual maps guide precise lesion localization and segmentation through a patch-based cross-attention mechanism that integrates regional spatial and pixel-level features. Additionally, the RCU incorporates patch-level importance scoring to enhance feature fusion by leveraging global spatial information from the backbone. Experiments on two publicly available medical image segmentation datasets, including brain stroke lesion and coronary artery calcification datasets, demonstrate that our GRCSF outperforms state-of-the-art methods, confirming its effectiveness across diverse lesion types and its potential as a generalizable lesion segmentation solution.

eess.IV↗

arXiv2025

TVC: Tokenized Video Compression with Ultra-Low Bit Rate

Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamics and stringent bit rate constraints. In this paper, we present tokenized video compression (TVC), a token-based dual-stream framework designed to operate effectively at ultra-low bit rates. TVC leverages the Cosmos video tokenizer to extract both discrete and continuous token streams. The discrete tokens are partially masked using a strategic masking scheme and then compressed losslessly with a discrete checkerboard context model to reduce transmission overhead. The masked tokens are reconstructed by a decoder-only Transformer with spatiotemporal token prediction. In parallel, the continuous tokens are quantized and compressed using a continuous checkerboard context model, providing complementary continuous information at ultra-low bit rates. At the decoder side, the two streams are fused with a ControlNet-based multi-scale integration module, ensuring high perceptual quality alongside stable fidelity in reconstruction. Overall, this work illustrates the practicality of tokenized video compression and points to new directions for semantics-aware, token-native approaches.

eess.IV↗

arXiv2025

Progress and new challenges in image-based profiling

For over two decades, image-based profiling has revolutionized cell phenotype analysis. Image-based profiling processes rich, high-throughput, microscopy data into thousands of unbiased measurements that reveal phenotypic patterns powerful for drug discovery, functional genomics, and cell state classification. Here, we review the evolving computational landscape of image-based profiling, detailing the bioinformatics processes involved from feature extraction to normalization and batch correction. We discuss how deep learning has fundamentally reshaped the field. We examine key methodological advancements, such as single-cell analysis, the development of robust similarity metrics, and the expansion into new modalities like optical pooled screening, temporal imaging, and 3D organoid profiling. We also highlight the growth of public benchmarks and open-source software ecosystems as a key driver for fostering reproducibility and collaboration. Despite these advances, the field still faces substantial challenges, particularly in developing methods for emerging temporal and 3D data modalities, establishing robust quality control standards and workflows, and interpreting the processed features. By focusing on the technical evolution of image-based profiling rather than the wide-ranging biological applications, our aim with this review is to provide researchers with a roadmap for navigating the progress and new challenges in this rapidly advancing domain.

q-bio.QM↗

arXiv2025

$\mathtt{M^3VIR}$: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation

The gaming and entertainment industry is rapidly evolving, driven by immersive experiences and the integration of generative AI (GAI) technologies. Training such models effectively requires large-scale datasets that capture the diversity and context of gaming environments. However, existing datasets are often limited to specific domains or rely on artificial degradations, which do not accurately capture the unique characteristics of gaming content. Moreover, benchmarks for controllable video generation remain absent. To address these limitations, we introduce $\mathtt{M^3VIR}$, a large-scale, multi-modal, multi-view dataset specifically designed to overcome the shortcomings of current resources. Unlike existing datasets, $\mathtt{M^3VIR}$ provides diverse, high-fidelity gaming content rendered with Unreal Engine 5, offering authentic ground-truth LR-HR paired and multi-view frames across 80 scenes in 8 categories. It includes $\mathtt{M^3VIR\_MR}$ for super-resolution (SR), novel view synthesis (NVS), and combined NVS+SR tasks, and $\mathtt{M^3VIR\_{MS}}$, the first multi-style, object-level ground-truth set enabling research on controlled video generation. Additionally, we benchmark several state-of-the-art SR and NVS methods to establish performance baselines. While no existing approaches directly handle controlled video generation, $\mathtt{M^3VIR}$ provides a benchmark for advancing this area. By releasing the dataset, we aim to facilitate research in AI-powered restoration, compression, and controllable content generation for next-generation cloud gaming and entertainment.

cs.CV↗

arXiv2025

Unleashing Perception-Time Scaling to Multimodal Reasoning Models

Recent advances in inference-time scaling, particularly those leveraging reinforcement learning with verifiable rewards, have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs). Inspired by this success, similar strategies have been applied to multimodal reasoning, yet their impact on visual perception remains unclear. To investigate this gap, we introduce DisTANCE, a perception-centric benchmark for visual estimation tasks. Evaluation results show that LVLMs exhibit limited estimation precision, and inference-time scaling offers only marginal gains. We attribute this to the fast perception paradigm of current LVLMs, where visual understanding is treated as a one-shot output without modeling the underlying perceptual process. To address this, we propose Perception-Time Scaling (PTS), a novel paradigm that encourages token-rich perception and decomposes complex perception problems into intermediate tractable sub-problems, thereby enabling perception to align with and benefit from inference-time scaling. Combined with reinforcement learning techniques, PTS significantly improves perception accuracy, raising high-precision performance on DisTANCE from 8.0% to 64.7%, and generalizes well to out-of-domain tasks. Surprisingly, even though PTS data are purely synthetic, combining them with math reasoning data yields consistent gains in both reasoning and real-world perception benchmarks. Further analysis reveals that PTS introduces more perception-related tokens and increases the model's attention to image tokens. Our code and data will be publicly released.

cs.CV↗