Zhibo Chen

Tao Yu, Runseng Feng, Ruoyu Feng et al.

Modern image inpainting systems, despite the significant progress, often struggle with mask selection and holes filling. Based on Segment-Anything Model (SAM), we make the first attempt to the mask-free image inpainting and propose a new paradigm of ``clicking and filling'', which is named as Inpaint Anything (IA). The core idea behind IA is to combine the strengths of different models in order to build a very powerful and user-friendly pipeline for solving inpainting-related problems. IA supports three main features: (i) Remove Anything: users could click on an object and IA will remove it and smooth the ``hole'' with the context; (ii) Fill Anything: after certain objects removal, users could provide text-based prompts to IA, and then it will fill the hole with the corresponding generative content via driving AIGC models like Stable Diffusion; (iii) Replace Anything: with IA, users have another option to retain the click-selected object and replace the remaining background with the newly generated scenes. We are also very willing to help everyone share and promote new projects based on our Inpaint Anything (IA). Our codes are available at https://github.com/geekyutao/Inpaint-Anything.

Xin Li, Yulin Ren, Xin Jin et al.

Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation. Recently, the diffusion model has achieved significant advancements in the visual generation of AIGC, thereby raising an intuitive question, "whether diffusion model can boost image restoration". To answer this, some pioneering studies attempt to integrate diffusion models into the image restoration task, resulting in superior performances than previous GAN-based methods. Despite that, a comprehensive and enlightening survey on diffusion model-based image restoration remains scarce. In this paper, we are the first to present a comprehensive review of recent diffusion model-based methods on image restoration, encompassing the learning paradigm, conditional strategy, framework design, modeling strategy, and evaluation. Concretely, we first introduce the background of the diffusion model briefly and then present two prevalent workflows that exploit diffusion models in image restoration. Subsequently, we classify and emphasize the innovative designs using diffusion models for both IR and blind/real-world IR, intending to inspire future development. To evaluate existing methods thoroughly, we summarize the commonly-used dataset, implementation details, and evaluation metrics. Additionally, we present the objective comparison for open-sourced methods across three tasks, including image super-resolution, deblurring, and inpainting. Ultimately, informed by the limitations in existing works, we propose five potential and challenging directions for the future research of diffusion model-based IR, including sampling efficiency, model compression, distortion simulation and estimation, distortion invariant learning, and framework design.

Tao Yu, Zhihe Lu, Xin Jin et al.

Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the well-learned knowledge structure of the VLMs should be inherited appropriately when being transferred to downstream tasks with limited data. However, most existing efficient transfer learning (ETL) approaches for VLMs either damage or are excessively biased towards the prior knowledge, e.g., prompt tuning (PT) discards the pre-trained text-based classifier and builds a new one while adapter-style tuning (AT) fully relies on the pre-trained features. To address this, we propose a new efficient tuning approach for VLMs named Task Residual Tuning (TaskRes), which performs directly on the text-based classifier and explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. Specifically, TaskRes keeps the original classifier weights from the VLMs frozen and obtains a new classifier for the target task by tuning a set of prior-independent parameters as a residual to the original one, which enables reliable prior knowledge preservation and flexible task-specific knowledge exploration. The proposed TaskRes is simple yet effective, which significantly outperforms previous ETL methods (e.g., PT and AT) on 11 benchmark datasets while requiring minimal effort for the implementation. Our code is available at https://github.com/geekyutao/TaskRes.

Xin Li, Dongze Lian, Zhihe Lu et al.

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additional parameters are introduced to excavate the task-specific knowledge based on the general and powerful representation of VLMs. However, most adapter-style works face two limitations: (i) modeling task-specific knowledge with a single modality only; and (ii) overlooking the exploitation of the inter-class relationships in downstream tasks, thereby leading to sub-optimal solutions. To mitigate that, we propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge (i.e., the correlation of different semantics/classes in textual and visual modalities) with a dual knowledge graph. In particular, the dual knowledge graph is established with two sub-graphs, i.e., a textual knowledge sub-graph, and a visual knowledge sub-graph, where the nodes and edges represent the semantics/classes and their correlations in two modalities, respectively. This enables the textual feature of each prompt to leverage the task-specific structure knowledge from both textual and visual modalities, yielding a more effective classifier for downstream tasks. Extensive experimental results on 11 benchmark datasets reveal that our GraphAdapter significantly outperforms previous adapter-based methods. The code will be released at https://github.com/lixinustc/GraphAdapter

Ruoyu Feng, Xin Jin, Zongyu Guo et al. · microsoft-research

Image Coding for Machines (ICM) aims to compress images for AI tasks analysis rather than meeting human perception. Learning a kind of feature that is both general (for AI tasks) and compact (for compression) is pivotal for its success. In this paper, we attempt to develop an ICM framework by learning universal features while also considering compression. We name such features as omnipotent features and the corresponding framework as Omni-ICM. Considering self-supervised learning (SSL) improves feature generalization, we integrate it with the compression task into the Omni-ICM framework to learn omnipotent features. However, it is non-trivial to coordinate semantics modeling in SSL and redundancy removing in compression, so we design a novel information filtering (IF) module between them by co-optimization of instance distinguishment and entropy minimization to adaptively drop information that is weakly related to AI tasks (e.g., some texture redundancy). Different from previous task-specific solutions, Omni-ICM could directly support AI tasks analysis based on the learned omnipotent features without joint training or extra transformation. Albeit simple and intuitive, Omni-ICM significantly outperforms existing traditional and learning-based codecs on multiple fundamental vision tasks.

Bingchen Li, Xin Li, Yiting Lu et al.

Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to restore the distorted image with the simple cooperation of super-resolution and compression artifacts removing. In this paper, we take a step forward to propose the Hierarchical Swin Transformer (HST) network to restore the low-resolution compressed image, which jointly captures the hierarchical feature representations and enhances each-scale representation with Swin transformer, respectively. Moreover, we find that the pretraining with Super-resolution (SR) task is vital in compressed image super-resolution. To explore the effects of different SR pretraining, we take the commonly-used SR tasks (e.g., bicubic and different real super-resolution simulations) as our pretraining tasks, and reveal that SR plays an irreplaceable role in the compressed image super-resolution. With the cooperation of HST and pre-training, our HST achieves the fifth place in AIM 2022 challenge on the low-quality compressed image super-resolution track, with the PSNR of 23.51dB. Extensive experiments and ablation studies have validated the effectiveness of our proposed methods. The code and models are available at https://github.com/USTC-IMCL/HST-for-Compressed-Image-SR.

Xin Li, Bingchen Li, Xin Jin et al.

In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations. Our method, termed Distortion Invariant representation Learning (DIL), treats each distortion type and degree as one specific confounder, and learns the distortion-invariant representation by eliminating the harmful confounding effect of each degradation. We derive our DIL with the back-door criterion in causality by modeling the interventions of different distortions from the optimization perspective. Particularly, we introduce counterfactual distortion augmentation to simulate the virtual distortion types and degrees as the confounders. Then, we instantiate the intervention of each distortion with a virtual model updating based on corresponding distorted images, and eliminate them from the meta-learning perspective. Extensive experiments demonstrate the effectiveness of our DIL on the generalization capability for unseen distortion types and degrees. Our code will be available at https://github.com/lixinustc/Causal-IR-DIL.

Guoqiang Wei, Zhizheng Zhang, Cuiling Lan et al.

The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of backbone architecture development. In this work, we propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate flexible contextual information distributed across different channels from other tokens into the given query token. This fundamental operator actively predicts where to capture useful contexts and learns how to fuse the captured contexts with the query token at channel level. In this way, the spatial range of token-mixing can be expanded to a global scope with limited computational complexity, where the way of token-mixing is reformed. We take ATM as the primary operator and assemble ATMs into a cascade architecture, dubbed ATMNet. Extensive experiments demonstrate that ATMNet is generally applicable and comprehensively surpasses different families of SOTA vision backbones by a clear margin on a broad range of vision tasks, including visual recognition and dense prediction tasks. Code is available at https://github.com/microsoft/ActiveMLP.

Zongyu Guo, Cuiling Lan, Zhizheng Zhang et al.

Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Neural Processes (NPs), which model the distributions over functions conditioned on partial observations (context set), provide a practical solution for fast inference of continuous functions. However, existing NP architectures suffer from inferior modeling capability for complex signals. In this paper, we propose an efficient NP framework dubbed Versatile Neural Processes (VNP), which largely increases the capability of approximating functions. Specifically, we introduce a bottleneck encoder that produces fewer and informative context tokens, relieving the high computational cost while providing high modeling capability. At the decoder side, we hierarchically learn multiple global latent variables that jointly model the global structure and the uncertainty of a function, enabling our model to capture the distribution of complex signals. We demonstrate the effectiveness of the proposed VNP on a variety of tasks involving 1D, 2D and 3D signals. Particularly, our method shows promise in learning accurate INRs w.r.t. a 3D scene without further finetuning. Code is available at https://github.com/ZongyuGuo/Versatile-NP .

Cong Wang, Hanxin Zhu, Jiayi Luo et al.

Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincing. Nevertheless, the dynamics induced by pixel-level fitting do not naturally accommodate the regularities that govern real-world motion and interaction, resulting in persistent shortcomings in physical plausibility. To address this limitation, we propose \textbf{PILA} (Physics-Informed Latent Alignment), a framework that injects physics-structured latent guidance into the frozen flow-matching dynamics of pretrained video models. Specifically, PILA first employs anchored field estimation to map frozen-generator latents into an operational physical attribute bank organized by field-proxy slots, using observable motion as a kinematic anchor for constructing less directly observed proxies. To handle the heterogeneity of real-world dynamics, PILA adopts a mixture-of-experts design over physical categories. Label-prior masked expert routing selects category-specific operator experts, whose refinements are regularized by operational residuals abstracted from physical relations. Finally, the refined proxies are fused into the physical attribute bank and decoded into a correction to the flow-matching vector field, injecting physics-aware guidance while preserving the visual prior of the pretrained backbone. With staged adapter training on Wan 2.1-1.3B and direct transfer of the learned adapter to Wan 2.2-14B, PILA achieves state-of-the-art results on VBench-2.0, VideoPhy-2, and PhyGenBench in both visual quality and benchmark-measured physical plausibility.

Xin Li, Yeying Jin, Suhang Yao et al.

This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this challenge attracted a wide range of impressive solutions, all developed and evaluated on our real-world Raindrop Clarity dataset~\cite{jin2024raindrop}. For this edition, we adjust the dataset with 14,139 images for training, 407 images for validation, and 593 images for testing. The primary goal of this challenge is to establish a strong and practical benchmark for the removal of raindrops under various illumination and focus conditions. In total, 168 teams have registered for the competition, and 17 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating the growing progress in this challenging task.

Xin Li, Jiachao Gong, Xijun Wang et al.

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

Shiqi Lin, Zhizheng Zhang, Zhipeng Huang et al.

Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge. Some theoretical studies have uncovered that DNNs have preferences for some frequency components in the learning process and indicated that this may affect the robustness of learned features. In this paper, we propose Deep Frequency Filtering (DFF) for learning domain-generalizable features, which is the first endeavour to explicitly modulate the frequency components of different transfer difficulties across domains in the latent space during training. To achieve this, we perform Fast Fourier Transform (FFT) for the feature maps at different layers, then adopt a light-weight module to learn attention masks from the frequency representations after FFT to enhance transferable components while suppressing the components not conducive to generalization. Further, we empirically compare the effectiveness of adopting different types of attention designs for implementing DFF. Extensive experiments demonstrate the effectiveness of our proposed DFF and show that applying our DFF on a plain baseline outperforms the state-of-the-art methods on different domain generalization tasks, including close-set classification and open-set retrieval.

Yulin Ren, Xin Li, Mengxi Guo et al.

We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamba are crucial for effective contextual knowledge modeling in the restoration process despite it relying on selective state space modeling for all tokens. In this work, we propose an efficient dual-interleaved scanning paradigm (DIS) for CSR, which is composed of two scanning strategies: (i) hierarchical interleaved scanning is designed to comprehensively capture and utilize the most potential contextual information within an image by simultaneously taking advantage of the local window-based and sequential scanning methods; (ii) horizontal-to-vertical interleaved scanning is proposed to reduce the computational cost by leaving the redundancy between the scanning of different directions. To overcome the non-uniform compression artifacts, we also propose position-aligned cross-scale scanning to model multi-scale contextual information. Experimental results on multiple benchmarks have shown the great performance of our MambaCSR in the compressed image super-resolution task. The code will be soon available in~\textcolor{magenta}{\url{https://github.com/renyulin-f/MambaCSR}}.

Yiting Lu, Jun Fu, Xin Li et al.

Coronary CT Angiography (CCTA) is susceptible to various distortions (e.g., artifacts and noise), which severely compromise the exact diagnosis of cardiovascular diseases. The appropriate CCTA Vessel-level Image Quality Assessment (CCTA VIQA) algorithm can be used to reduce the risk of error diagnosis. The primary challenges of CCTA VIQA are that the local part of coronary that determines final quality is hard to locate. To tackle the challenge, we formulate CCTA VIQA as a multiple-instance learning (MIL) problem, and exploit Transformer-based MIL backbone (termed as T-MIL) to aggregate the multiple instances along the coronary centerline into the final quality. However, not all instances are informative for final quality. There are some quality-irrelevant/negative instances intervening the exact quality assessment(e.g., instances covering only background or the coronary in instances is not identifiable). Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA. Based on the above two modules, we propose a Reinforced Transformer Network (RTN) for automatic CCTA VIQA based on end-to-end optimization. Extensive experimental results demonstrate that our proposed method achieves the state-of-the-art performance on the real-world CCTA dataset, exceeding previous MIL methods by a large margin.

Jianzhao Liu, Xin Li, Yanding Peng et al.

Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only help to verify the performance of various compression algorithms but also help to guide the compression optimization in turn. In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space. It is known that the compression artifacts are usually non-uniformly distributed with diverse distortion types and degrees. To warp the compressed images into the shared representation space while maintaining the complex distortion information, we extract the hierarchical feature representations from each stage of the Swin Transformer. Besides, we utilize cross attention operation to map the extracted feature representations into a learned Swin distance space. Experimental results show that the proposed metric achieves higher consistency with human's perceptual judgment compared with both traditional methods and learning-based methods on CLIC datasets.

Yiting Lu, Xin Li, Jianzhao Liu et al.

Deep neural networks (DNNs) have shown great potential in non-reference image quality assessment (NR-IQA). However, the annotation of NR-IQA is labor-intensive and time-consuming, which severely limits their application especially for authentic images. To relieve the dependence on quality annotation, some works have applied unsupervised domain adaptation (UDA) to NR-IQA. However, the above methods ignore that the alignment space used in classification is sub-optimal, since the space is not elaborately designed for perception. To solve this challenge, we propose an effective perception-oriented unsupervised domain adaptation method StyleAM for NR-IQA, which transfers sufficient knowledge from label-rich source domain data to label-free target domain images via Style Alignment and Mixup. Specifically, we find a more compact and reliable space i.e., feature style space for perception-oriented UDA based on an interesting/amazing observation, that the feature style (i.e., the mean and variance) of the deep layer in DNNs is exactly associated with the quality score in NR-IQA. Therefore, we propose to align the source and target domains in a more perceptual-oriented space i.e., the feature style space, to reduce the intervention from other quality-irrelevant feature factors. Furthermore, to increase the consistency between quality score and its feature style, we also propose a novel feature augmentation strategy Style Mixup, which mixes the feature styles (i.e., the mean and variance) before the last layer of DNNs together with mixing their labels. Extensive experimental results on two typical cross-domain settings (i.e., synthetic to authentic, and multiple distortions to one distortion) have demonstrated the effectiveness of our proposed StyleAM on NR-IQA.

Xin Li, Cuiling Lan, Guoqiang Wei et al.

Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distribution data). To mitigate this issue, we propose a novel method, Semantic-aware Message Broadcasting (SAMB), which enables more informative and flexible feature alignment for unsupervised domain adaptation (UDA). Particularly, we study the attention module in the vision transformer and notice that the alignment space using one global class token lacks enough flexibility, where it interacts information with all image tokens in the same manner but ignores the rich semantics of different regions. In this paper, we aim to improve the richness of the alignment features by enabling semantic-aware adaptive message broadcasting. Particularly, we introduce a group of learned group tokens as nodes to aggregate the global information from all image tokens, but encourage different group tokens to adaptively focus on the message broadcasting to different semantic regions. In this way, our message broadcasting encourages the group tokens to learn more informative and diverse information for effective domain alignment. Moreover, we systematically study the effects of adversarial-based feature alignment (ADA) and pseudo-label based self-training (PST) on UDA. We find that one simple two-stage training strategy with the cooperation of ADA and PST can further improve the adaptation capability of the vision transformer. Extensive experiments on DomainNet, OfficeHome, and VisDA-2017 demonstrate the effectiveness of our methods for UDA.

Xin Li, Bingchen Li, Yeying Jin et al.

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

Jiayi Luo, Qiyan Liu, Tengyang Wang et al.

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid redundant recomputation across generation steps. Nevertheless, its growth with generation length introduces increasing memory and error accumulation, limiting the scalability of AR models to even longer sequences. Existing KV cache compression methods mitigate this issue by selectively retaining only video tokens deemed important. However, most existing methods assess token importance using short-horizon signals derived from the current or historical generation context, making these methods prone to overlooking tokens that appear unimportant at early steps but later become critical for future frames. In this work, we identify an important property of trained AR video models: although RoPE-modulated queries evolve across autoregressive steps, the underlying canonical pre-RoPE query distribution remains remarkably stable throughout the video generation process. This approximate stationarity implies that future query distributions are estimable from historical statistics, enabling principled future-aware cache decisions without any additional training. Building on this insight, we propose Future Forcing, a training-free future-aware KV cache policy for AR video generation. Specifically, Future Forcing first constructs a future query proxy from historical statistics, then scores KV cache tokens by their importance under this proxy, and finally merges redundant token pairs within the affine subspace induced by the future query. Extensive experiments show that Future Forcing improves long-horizon consistency under limited KV caches, achieving up to 1.49 improvement in subject consistency on VBench-Long for 60s generation over existing AR video KV cache policies.

Ruoyu Feng, Wenming Weng, Yanhui Wang et al.

In this paper, we present CCEdit, a versatile generative video editing framework based on diffusion models. Our approach employs a novel trident network structure that separates structure and appearance control, ensuring precise and creative editing capabilities. Utilizing the foundational ControlNet architecture, we maintain the structural integrity of the video during editing. The incorporation of an additional appearance branch enables users to exert fine-grained control over the edited key frame. These two side branches seamlessly integrate into the main branch, which is constructed upon existing text-to-image (T2I) generation models, through learnable temporal layers. The versatility of our framework is demonstrated through a diverse range of choices in both structure representations and personalized T2I models, as well as the option to provide the edited key frame. To facilitate comprehensive evaluation, we introduce the BalanceCC benchmark dataset, comprising 100 videos and 4 target prompts for each video. Our extensive user studies compare CCEdit with eight state-of-the-art video editing methods. The outcomes demonstrate CCEdit's substantial superiority over all other methods.

Xiaoshuai Fan, Xin Li, Zhibo Chen

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

Hanxin Zhu, Henan Wang, Zhibo Chen

Traditional representations for light fields can be separated into two types: explicit representation and implicit representation. Unlike explicit representation that represents light fields as Sub-Aperture Images (SAIs) based arrays or Micro-Images (MIs) based lenslet images, implicit representation treats light fields as neural networks, which is inherently a continuous representation in contrast to discrete explicit representation. However, at present almost all the implicit representations for light fields utilize SAIs to train an MLP to learn a pixel-wise mapping from 4D spatial-angular coordinate to pixel colors, which is neither compact nor of low complexity. Instead, in this paper we propose MiNL, a novel MI-wise implicit neural representation for light fields that train an MLP + CNN to learn a mapping from 2D MI coordinates to MI colors. Given the micro-image's coordinate, MiNL outputs the corresponding micro-image's RGB values. Light field encoding in MiNL is just training a neural network to regress the micro-images and the decoding process is a simple feedforward operation. Compared with common pixel-wise implicit representation, MiNL is more compact and efficient that has faster decoding speed (\textbf{$\times$80$\sim$180} speed-up) as well as better visual quality (\textbf{1$\sim$4dB} PSNR improvement on average).

Sen Liang, Cong Wang, Fengbin Guan et al.

Visual and acoustic events in the physical world are inherently coupled, yet existing video editing methods typically adopt decoupled pipelines, lacking bidirectional modality interaction. This results in two key limitations: (i) audio-visual desynchronization and (ii) contextual conflicts between generated audio and preserved content. To address these, we propose SpongeBob, the first end-to-end audio-visual joint editing framework featuring bidirectional cross-modal interaction. For synchronization, a Sync-Aware Mechanism aligns visual edits with sound events via bidirectional attention, temporal alignment, and spatial constraints. For contextual consistency, a Context-Aware Module leverages acoustic and visual context attention to prevent semantic clashes. Additionally, we introduce Sync-Preserving Training and Guidance (SPTG) to enhance alignment without degrading quality. Due to the scarcity of paired data, we construct a scalable data pipeline and a large-scale subject-level dataset. We also propose SpongeBob-Bench for systematic evaluation. Experiments show SpongeBob significantly outperforms existing baselines, improving Sync-C by 30% and Ctx-F1 by 12.5%. Our project page is available at: https://hy-spongebob.github.io/.

Yulin Ren, Xin Li, Bingchen Li et al.

We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for different image codecs, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/.

Hanxin Zhu, Tianyu He, Anni Tang et al.

Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual concepts within the generated video, such as the motion and appearance of specific characters and the movement of viewpoints. In this work, we propose a novel paradigm that generates each concept in 3D representation separately and then composes them with priors from Large Language Models (LLM) and 2D diffusion models. Specifically, given an input textual prompt, our scheme consists of three stages: 1) We leverage LLM as the director to first decompose the complex query into several sub-prompts that indicate individual concepts within the video~(\textit{e.g.}, scene, objects, motions), then we let LLM to invoke pre-trained expert models to obtain corresponding 3D representations of concepts. 2) To compose these representations, we prompt multi-modal LLM to produce coarse guidance on the scales and coordinates of trajectories for the objects. 3) To make the generated frames adhere to natural image distribution, we further leverage 2D diffusion priors and use Score Distillation Sampling to refine the composition. Extensive experiments demonstrate that our method can generate high-fidelity videos from text with diverse motion and flexible control over each concept. Project page: \url{https://aka.ms/c3v}.

Jianzhao Liu, Xin Li, Shukun An et al.

Existing learning-based methods for blind image quality assessment (BIQA) are heavily dependent on large amounts of annotated training data, and usually suffer from a severe performance degradation when encountering the domain/distribution shift problem. Thanks to the development of unsupervised domain adaptation (UDA), some works attempt to transfer the knowledge from a label-sufficient source domain to a label-free target domain under domain shift with UDA. However, it requires the coexistence of source and target data, which might be impractical for source data due to the privacy or storage issues. In this paper, we take the first step towards the source-free unsupervised domain adaptation (SFUDA) in a simple yet efficient manner for BIQA to tackle the domain shift without access to the source data. Specifically, we cast the quality assessment task as a rating distribution prediction problem. Based on the intrinsic properties of BIQA, we present a group of well-designed self-supervised objectives to guide the adaptation of the BN affine parameters towards the target domain. Among them, minimizing the prediction entropy and maximizing the batch prediction diversity aim to encourage more confident results while avoiding the trivial solution. Besides, based on the observation that the IQA rating distribution of single image follows the Gaussian distribution, we apply Gaussian regularization to the predicted rating distribution to make it more consistent with the nature of human scoring. Extensive experimental results under cross-domain scenarios demonstrated the effectiveness of our proposed method to mitigate the domain shift.

Jinming Liu, Ruoyu Feng, Yunpeng Qi et al.

Recently, the field of Image Coding for Machines (ICM) has garnered heightened interest and significant advances thanks to the rapid progress of learning-based techniques for image compression and analysis. Previous studies often require training separate codecs to support various bitrate levels, machine tasks, and networks, thus lacking both flexibility and practicality. To address these challenges, we propose a rate-distortion-cognition controllable versatile image compression, which method allows the users to adjust the bitrate (i.e., Rate), image reconstruction quality (i.e., Distortion), and machine task accuracy (i.e., Cognition) with a single neural model, achieving ultra-controllability. Specifically, we first introduce a cognition-oriented loss in the primary compression branch to train a codec for diverse machine tasks. This branch attains variable bitrate by regulating quantization degree through the latent code channels. To further enhance the quality of the reconstructed images, we employ an auxiliary branch to supplement residual information with a scalable bitstream. Ultimately, two branches use a `$βx + (1 - β) y$' interpolation strategy to achieve a balanced cognition-distortion trade-off. Extensive experiments demonstrate that our method yields satisfactory ICM performance and flexible Rate-Distortion-Cognition controlling.

Xinge Peng, Yiting Lu, Xin Li et al.

We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding. Existing LMM-based IQA methods typically support only partial perception dimensions, such as quality description and question answering~(\textit{i.e.}, reasoning) or pixel-level grounding. This limitation largely stems from the absence of (i) a unified task and data formulation and (ii) effective optimization paradigms for multi-granularity learning. To address these limitations, we formulate a rigorous four-task paradigm covering global and local quality description, pixel-level grounding, and region-level referring. Based on this formulation, we construct a corresponding IQA dataset with a scalable and automatic annotation pipeline, thereby providing a solid foundation for unified multi-granularity learning. To further enable unified perception, we adopt a conflict-free two-stage design that progressively extends text-level multi-granularity understanding to pixel-level grounding: (i) the first stage equips the model with fine-grained text-level reasoning across multiple IQA tasks, and (ii) the second stage introduces a training-free text-to-point grounding paradigm, which bridges textual semantics and pixel-level perception by mapping token logits to spatial coordinates. Based on these efforts, we achieve IQA-Spider with unified multi-granularity explainable image quality assessment. Extensive experiments across multiple benchmarks demonstrate strong performance, validating the effectiveness and versatility of the proposed formulation and framework.

Xin Ding, Xinrui Wang, Yifan Yang et al.

Existing memory systems for embodied agents typically inject retrieved memory as static context at episode start, a paradigm we term Ahead-of-time Monolithic Memory Injection (AMMI). However, this static design quickly becomes misaligned with the agent's evolving state and may degrade lightweight executors below the no-memory baseline. To address this, we propose MemCompiler, which reframes memory utilization as State-Conditioned Memory Compilation. A learned Memory Compiler reads a structured Brief State capturing the agent's current execution state and dynamically selects and compiles only relevant memory into executable guidance. This guidance is delivered through a text channel and a latent Soft-Mem channel that preserves perceptual information not expressible in text. Across Alf World, EmbodiedBench, and ScienceWorld, MemCompiler consistently improves over no-memory across open-source backbones (up to +129%), matches or approaches frontier closed-source systems, and reduces per-step latency by 60%, demonstrating that state-aware memory compilation improves both effectiveness and efficiency.

Xin Li, Kun Yuan, Yajing Pei et al.

This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i.e., Kuaishou/Kwai Platform. The KVQ database is divided into three parts, including 2926 videos for training, 420 videos for validation, and 854 videos for testing. The purpose is to build new benchmarks and advance the development of S-UGC VQA. The competition had 200 participants and 13 teams submitted valid solutions for the final testing phase. The proposed solutions achieved state-of-the-art performances for S-UGC VQA. The project can be found at https://github.com/lixinustc/KVQChallenge-CVPR-NTIRE2024.

Jinming Liu, Yuntao Wei, Junyan Lin et al.

We present a new image compression paradigm to achieve ``intelligently coding for machine'' by cleverly leveraging the common sense of Large Multimodal Models (LMMs). We are motivated by the evidence that large language/multimodal models are powerful general-purpose semantics predictors for understanding the real world. Different from traditional image compression typically optimized for human eyes, the image coding for machines (ICM) framework we focus on requires the compressed bitstream to more comply with different downstream intelligent analysis tasks. To this end, we employ LMM to \textcolor{red}{tell codec what to compress}: 1) first utilize the powerful semantic understanding capability of LMMs w.r.t object grounding, identification, and importance ranking via prompts, to disentangle image content before compression, 2) and then based on these semantic priors we accordingly encode and transmit objects of the image in order with a structured bitstream. In this way, diverse vision benchmarks including image classification, object detection, instance segmentation, etc., can be well supported with such a semantically structured bitstream. We dub our method ``\textit{SDComp}'' for ``\textit{S}emantically \textit{D}isentangled \textit{Comp}ression'', and compare it with state-of-the-art codecs on a wide variety of different vision tasks. SDComp codec leads to more flexible reconstruction results, promised decoded visual quality, and a more generic/satisfactory intelligent task-supporting ability.

Ruoyu Feng, Tao Yu, Xin Jin et al.

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has shown strong ability on zero-shot recognition, and parameter efficient tuning can further improve its performance on specific tasks. This work demonstrates that a simple domain prior boosts CLIP's zero-shot recognition in a specific domain. Besides, CLIP's adaptation relies less on source domain data due to its diverse pre-training dataset. Furthermore, we create a benchmark for zero-shot adaptation and pseudo-labeling based self-training with CLIP. Last but not least, we propose to improve the task generalization ability of CLIP from multiple unlabeled domains, which is a more practical and unique scenario. We believe our findings motivate a rethinking of domain adaptation benchmarks and the associated role of related algorithms in the era of CLIP.

Xin Li, Kun Yuan, Bingchen Li et al.

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

Bingchen Li, Xin Li, Yiting Lu et al.

Blind Compressed Image Restoration (CIR) has garnered significant attention due to its practical applications. It aims to mitigate compression artifacts caused by unknown quality factors, particularly with JPEG codecs. Existing works on blind CIR often seek assistance from a quality factor prediction network to facilitate their network to restore compressed images. However, the predicted numerical quality factor lacks spatial information, preventing network adaptability toward image contents. Recent studies in prompt-learning-based image restoration have showcased the potential of prompts to generalize across varied degradation types and degrees. This motivated us to design a prompt-learning-based compressed image restoration network, dubbed PromptCIR, which can effectively restore images from various compress levels. Specifically, PromptCIR exploits prompts to encode compression information implicitly, where prompts directly interact with soft weights generated from image features, thus providing dynamic content-aware and distortion-aware guidance for the restoration process. The light-weight prompts enable our method to adapt to different compression levels, while introducing minimal parameter overhead. Overall, PromptCIR leverages the powerful transformer-based backbone with the dynamic prompt module to proficiently handle blind CIR tasks, winning first place in the NTIRE 2024 challenge of blind compressed image enhancement track. Extensive experiments have validated the effectiveness of our proposed PromptCIR. The code is available at https://github.com/lbc12345/PromptCIR-NTIRE24.

Bingchen Li, Zhixin Wang, Fan Li et al.

Old photos preserve invaluable historical memories, making their restoration and colorization highly desirable. While existing restoration models can address some degradation issues like denoising and scratch removal, they often struggle with accurate colorization. This limitation arises from the unique degradation inherent in old photos, such as faded brightness and altered color hues, which are different from modern photo distributions, creating a substantial domain gap during colorization. In this paper, we propose a novel old photo colorization framework based on the generative diffusion model FLUX. Our approach introduces a structure-color decoupling strategy that separates structure preservation from color restoration, enabling accurate colorization of old photos while maintaining structural consistency. We further enhance the model with a progressive Direct Preference Optimization (Pro-DPO) strategy, which allows the model to learn subtle color preferences through coarse-to-fine transitions in color augmentation. Additionally, we address the limitations of text-based prompts by introducing visual semantic prompts, which extract fine-grained semantic information directly from old photos, helping to eliminate the color bias inherent in old photos. Experimental results on both synthetic and real datasets demonstrate that our approach outperforms existing state-of-the-art colorization methods, including closed-source commercial models, producing high-quality and vivid colorization.

Xin Li, Daoli Xu, Wei Luo et al.

This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality assessment, we form a dataset of human-oriented semantic quality assessment, termed the SeIQA dataset. This dataset is divided into three parts for this competition: (i) training data: 510 pairs of degraded images and their corresponding ground truth references; (ii) validation data: 80 pairs of degraded images and their corresponding ground-truth references; (iii) testing data: 160 pairs of degraded images and their corresponding ground-truth references. The primary objective of this challenge is to establish a new and powerful benchmark for human-oriented semantic image quality assessment. There are a total of 58 teams registered in this competition, and 6 teams submitted valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the SeIQA dataset.

Guangqi Xie, Xin Li, Xiaohan Pan et al.

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

Hongjin Chen, Shangyun Jiang, Tonghua Su et al.

Vision-language models (VLMs) and generative world models are opening new opportunities for embodied navigation. VLMs are increasingly used as direct planners or trajectory predictors, while world models support look-ahead reasoning by imagining future views. Yet predicting a reliable trajectory from a single egocentric observation remains challenging. Current VLMs often generate unstable trajectories, and world models, though able to synthesize plausible futures, do not directly provide the grounded signals needed for navigation learning. This raises a central question: how can generated futures be turned into supervision for grounded trajectory prediction? We present WorldMAP, a teacher--student framework that converts world-model-generated futures into persistent semantic-spatial structure and planning-derived supervision. Its world-model-driven teacher builds semantic-spatial memory from generated videos, grounds task-relevant targets and obstacles, and produces trajectory pseudo-labels through explicit planning. A lightweight student with a multi-hypothesis trajectory head is then trained to predict navigation trajectories directly from vision-language inputs. On Target-Bench, WorldMAP achieves the best ADE and FDE among compared methods, reducing ADE by 18.0% and FDE by 42.1% relative to the best competing baseline, while lifting a small open-source VLM to DTW performance competitive with proprietary models. More broadly, the results suggest that, in embodied navigation, the value of world models may lie less in supplying action-ready imagined evidence than in synthesizing structured supervision for navigation learning.

Chenyang An, Zhibo Chen, Qihao Ye et al.

Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i.e. proof steps) to search through proof states. The current model, while trained solely on successful proof paths, faces a discrepancy at the inference stage, as it must sample and try various tactics at each proof state until finding success, unlike its training which does not incorporate learning from failed attempts. Intuitively, a tactic that leads to a failed search path would indicate that similar tactics should receive less attention during the following trials. In this paper, we demonstrate the benefit of training models that additionally learn from failed search paths. Facing the lack of such trial-and-error data in existing open-source theorem-proving datasets, we curate a dataset on intuitionistic propositional logic theorems and formalize it in Lean, such that we can reliably check the correctness of proofs. We compare our model trained on relatively short trial-and-error information (TrialMaster) with models trained only on the correct paths and discover that the former solves more unseen theorems with lower trial searches.

Yu Shang, Yinzhou Tang, Yiding Ma et al.

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The benchmark is available at: https://world-arena.ai.

Jiayi Luo, Jiayu Chen, Jiankun Wang et al.

Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, leading to the development of sparse attention technologies to improve efficiency. However, existing training-free sparse attention methods in video generation still face two unresolved limitations: ignoring layer heterogeneity in attention pruning and ignoring query-key coupling in block partitioning, which hinder a better quality-speedup trade-off. In this work, we uncover a critical insight that the attention sparsity of each layer is its intrinsic property, with minor effects across different inputs. Motivated by this, we propose SVOO, a training-free Sparse attention framework for fast Video generation via Offline layer-wise sparsity profiling and Online bidirectional co-clustering. Specifically, SVOO adopts a two-stage paradigm: (i) offline layer-wise sensitivity profiling to derive intrinsic per-layer pruning levels, and (ii) online block-wise sparse attention via a novel bidirectional co-clustering algorithm. Extensive experiments on seven widely used video generation models demonstrate that SVOO achieves a superior quality-speedup trade-off over state-of-the-art methods, delivering up to $1.93\times$ speedup while maintaining a PSNR of up to 29 dB on Wan2.1.

Yu Shang, Zhuohang Li, Yiding Ma et al.

While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their evaluation remains fragmented. Current evaluation of embodied world models has largely focused on perceptual fidelity (e.g., video generation quality), overlooking the functional utility of these models in downstream decision-making tasks. In this work, we introduce WorldArena, a unified benchmark designed to systematically evaluate embodied world models across both perceptual and functional dimensions. WorldArena assesses models through three dimensions: video perception quality, measured with 16 metrics across six sub-dimensions; embodied task functionality, which evaluates world models as data engines, policy evaluators, and action planners integrating with subjective human evaluation. Furthermore, we propose EWMScore, a holistic metric integrating multi-dimensional performance into a single interpretable index. Through extensive experiments on 14 representative models, we reveal a significant perception-functionality gap, showing that high visual quality does not necessarily translate into strong embodied task capability. WorldArena benchmark with the public leaderboard is released at https://worldarena.ai, providing a framework for tracking progress toward truly functional world models in embodied AI.

Sen Liang, Zhentao Yu, Zhengguang Zhou et al.

The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generation is widely applied in various fields, most existing models are limited to single scenarios and cannot perform diverse video generation and editing through dynamic content manipulation. We propose OmniV2V, a video model capable of generating and editing videos across different scenarios based on various operations, including: object movement, object addition, mask-guided video edit, try-on, inpainting, outpainting, human animation, and controllable character video synthesis. We explore a unified dynamic content manipulation injection module, which effectively integrates the requirements of the above tasks. In addition, we design a visual-text instruction module based on LLaVA, enabling the model to effectively understand the correspondence between visual content and instructions. Furthermore, we build a comprehensive multi-task data processing system. Since there is data overlap among various tasks, this system can efficiently provide data augmentation. Using this system, we construct a multi-type, multi-scenario OmniV2V dataset and its corresponding OmniV2V-Test benchmark. Extensive experiments show that OmniV2V works as well as, and sometimes better than, the best existing open-source and commercial models for many video generation and editing tasks.

Yiting Lu, Xin Li, Haoning Wu et al.

The rapid advancement of Large Multi-modal Foundation Models (LMM) has paved the way for the possible Explainable Image Quality Assessment (EIQA) with instruction tuning from two perspectives: overall quality explanation, and attribute-wise perception answering. However, existing works usually overlooked the conflicts between these two types of perception explanations during joint instruction tuning, leading to insufficient perception understanding. To mitigate this, we propose a new paradigm for perception-oriented instruction tuning, i.e., Q-Adapt, which aims to eliminate the conflicts and achieve the synergy between these two EIQA tasks when adapting LMM, resulting in enhanced multi-faceted explanations of IQA. Particularly, we propose a progressive instruction tuning strategy by dividing the adaption process of LMM for EIQA into two stages, where the first stage empowers the LMM with universal perception knowledge tailored for two tasks using an efficient transfer learning strategy, i.e., LoRA, and the second stage introduces the instruction-adaptive visual prompt tuning to dynamically adapt visual features for the different instructions from two tasks. In this way, our proposed Q-Adapt can achieve a lightweight visual quality evaluator, demonstrating comparable performance and, in some instances, superior results across perceptual-related benchmarks and commonly-used IQA databases. The source code is publicly available at https://github.com/yeppp27/Q-Adapt.

Yixin Gao, Xin Li, Xiaohan Pan et al.

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

Jingwen Sun, Wenyao Zhang, Zekun Qi et al.

Pretraining Vision-Language-Action (VLA) policies on internet-scale video is appealing, yet current latent-action objectives often learn the wrong thing: they remain anchored to pixel variation rather than action-relevant state transitions, making them vulnerable to appearance bias, nuisance motion, and information leakage. We introduce VLA-JEPA, a JEPA-style pretraining framework that sidesteps these pitfalls by design. The key idea is \emph{leakage-free state prediction}: a target encoder produces latent representations from future frames, while the student pathway sees only the current observation -- future information is used solely as supervision targets, never as input. By predicting in latent space rather than pixel space, VLA-JEPA learns dynamics abstractions that are robust to camera motion and irrelevant background changes. This yields a simple two-stage recipe -- JEPA pretraining followed by action-head fine-tuning -- without the multi-stage complexity of prior latent-action pipelines. Experiments on LIBERO, LIBERO-Plus, SimplerEnv and real-world manipulation tasks show that VLA-JEPA achieves consistent gains in generalization and robustness over existing methods.

Cong Wang, Hanxin Zhu, Xiao Tang et al.

Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that real-world object motion unfolds in three-dimensional space, while video observations provide only partial, view-dependent projections of such dynamics. To address these issues, we propose PhysVideo, a two-stage framework that first generates physics-aware orthogonal foreground videos and then synthesizes full videos with background. In the first stage, Phys4View leverages physics-aware attention to capture the influence of physical attributes on motion dynamics, and enhances spatio-temporal consistency by incorporating geometry-enhanced cross-view attention and temporal attention. In the second stage, VideoSyn uses the generated foreground videos as guidance and learns the interactions between foreground dynamics and background context for controllable video synthesis. To support training, we construct PhysMV, a dataset containing 40K scenes, each consisting of four orthogonal viewpoints, resulting in a total of 160K video sequences. Extensive experiments demonstrate that PhysVideo significantly improves physical realism and spatial-temporal coherence over existing video generation methods. Home page: https://anonymous.4open.science/w/Phys4D/.

Hanxin Zhu, Cong Wang, Peiyan Tu et al.

Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intelligence, embodied intelligence, and autonomous driving. While achieving remarkable progress, existing approaches to 3D world generation typically prioritize appearance prediction with limited modeling of the underlying geometry, leading to issues such as unreliable scene structure estimation and degraded cross-view consistency. To address these limitations, motivated by the coarse-to-fine nature of human visual perception, we propose GTA, a novel image-to-3D world generation method following a Geometry-Then-Appearance paradigm. Specifically, given a single input image, to improve the structural fidelity of synthesized 3D scenes, GTA adopts a two-stage framework with two dedicated video diffusion models, which first generate coarse geometric structure from novel viewpoints and then synthesize fine-grained appearance conditioned on the predicted geometry. To further enhance cross-view appearance consistency, we introduce a random latent shuffle strategy during the training process, along with a test-time scaling scheme that improves perceptual quality without compromising quantitative performance. Extensive experiments have demonstrated that our proposed method consistently outperforms existing approaches in terms of fidelity, visual quality, and geometric accuracy. Moreover, GTA is shown to be effective as a general enhancement module that further improves the generation quality of existing image-to-3D world pipelines, as well as supporting multiple downstream applications and exhibiting favorable data efficiency during model training, highlighting its versatility and broad applicability. Project page: https://hanxinzhu-lab.github.io/GTA/.

Haofan Wang, Yujia Xu, Yimeng Li et al.

Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible typographic elements, especially non-Latin alphabets, remains constrained. To address these limitations, we start from an naive assumption that text understanding is only a sufficient condition for text rendering, but not a necessary condition. Based on this, we present RepText, which aims to empower pre-trained monolingual text-to-image generation models with the ability to accurately render, or more precisely, replicate, multilingual visual text in user-specified fonts, without the need to really understand them. Specifically, we adopt the setting from ControlNet and additionally integrate language agnostic glyph and position of rendered text to enable generating harmonized visual text, allowing users to customize text content, font and position on their needs. To improve accuracy, a text perceptual loss is employed along with the diffusion loss. Furthermore, to stabilize rendering process, at the inference phase, we directly initialize with noisy glyph latent instead of random initialization, and adopt region masks to restrict the feature injection to only the text region to avoid distortion of the background. We conducted extensive experiments to verify the effectiveness of our RepText relative to existing works, our approach outperforms existing open-source methods and achieves comparable results to native multi-language closed-source models. To be more fair, we also exhaustively discuss its limitations in the end.