Zhihua Wang

Zhihua Wang, Yanping Li, Yizhang Liu

Correspondence pruning aims to identify inliers from an initial set of correspondences. Most existing Graph Neural Network (GNN)-based methods rely on geometric features mapped from coarse Euclidean coordinates, which struggle to capture the subtle geometric consistencies presented by inliers. While Mamba-based methods possess global receptive fields and long sequence modeling capabilities, they tend to accumulate substantial inconsistent features within the hidden state space, making it difficult to distinguish inliers from outliers. In this paper, we integrate frequency domain perception into this task for the first time and propose SFMambaNet, a novel Spectral-Frequency enhanced Mamba-based two-view correspondence pruning network. Our method is collaboratively composed of two components: First, we design a Local Spectral-Geometric Attention (LSGA) block. LSGA incorporates spectral positional encoding into local graph interactions and introduces multi-scale Mamba processing to enhance the capture of subtle geometric consistencies and improve local feature discriminability. Building upon this, we design a Spectral-Integrated Global Mamba (SIGM) block. SIGM embeds a frequency gating mechanism within the state space, utilizing the frequency information provided by LSGA to explicitly suppress high-frequency noise accumulation within hidden states and mitigate the propagation of inconsistent features. This enhances inlier-outlier separability and achieves robust global context modeling capabilities with nearly linear complexity. Extensive experiments demonstrate that SFMambaNet outperforms current state-of-the-art methods on several challenging tasks. The code is available at https://github.com/Kirito14IT/SFMambaNet.

Zhihua Wang, Keshuo Xu, Yang Yang et al.

Measuring perceptual color differences (CDs) is of great importance in modern smartphone photography. Despite the long history, most CD measures have been constrained by psychophysical data of homogeneous color patches or a limited number of simplistic natural photographic images. It is thus questionable whether existing CD measures generalize in the age of smartphone photography characterized by greater content complexities and learning-based image signal processors. In this paper, we put together so far the largest image dataset for perceptual CD assessment, in which the photographic images are 1) captured by six flagship smartphones, 2) altered by Photoshop, 3) post-processed by built-in filters of the smartphones, and 4) reproduced with incorrect color profiles. We then conduct a large-scale psychophysical experiment to gather perceptual CDs of 30,000 image pairs in a carefully controlled laboratory environment. Based on the newly established dataset, we make one of the first attempts to construct an end-to-end learnable CD formula based on a lightweight neural network, as a generalization of several previous metrics. Extensive experiments demonstrate that the optimized formula outperforms 33 existing CD measures by a large margin, offers reasonable local CD maps without the use of dense supervision, generalizes well to homogeneous color patch data, and empirically behaves as a proper metric in the mathematical sense. Our dataset and code are publicly available at https://github.com/hellooks/CDNet.

Jiaqi He, Zhihua Wang, Leon Wang et al.

Contemporary color difference (CD) measures for photographic images typically operate by comparing co-located pixels, patches in a ``perceptually uniform'' color space, or features in a learned latent space. Consequently, these measures inadequately capture the human color perception of misaligned image pairs, which are prevalent in digital photography (e.g., the same scene captured by different smartphones). In this paper, we describe a perceptual CD measure based on the multiscale sliced Wasserstein distance, which facilitates efficient comparisons between non-local patches of similar color and structure. This aligns with the modern understanding of color perception, where color and structure are inextricably interdependent as a unitary process of perceptual organization. Meanwhile, our method is easy to implement and training-free. Experimental results indicate that our CD measure performs favorably in assessing CDs in photographic images, and consistently surpasses competing models in the presence of image misalignment. Additionally, we empirically verify that our measure functions as a metric in the mathematical sense, and show its promise as a loss function for image and video color transfer tasks. The code is available at https://github.com/real-hjq/MS-SWD.

Shuyi Zhang, Ke Liu, Jingjun Gu et al.

Implicit Neural Representation (INR) has gained increasing popularity as a data representation method, serving as a prerequisite for innovative generation models. Unlike gradient-based methods, which exhibit lower efficiency in inference, the adoption of hyper-network for generating parameters in Multi-Layer Perceptrons (MLP), responsible for executing INR functions, has surfaced as a promising and efficient alternative. However, as a global continuous function, MLP is challenging in modeling highly discontinuous signals, resulting in slow convergence during the training phase and inaccurate reconstruction performance. Moreover, MLP requires massive representation parameters, which implies inefficiencies in data representation. In this paper, we propose a novel Attention-based Localized INR (ANR) composed of a localized attention layer (LAL) and a global MLP that integrates coordinate features with data features and converts them to meaningful outputs. Subsequently, we design an instance representation framework that delivers a transformer-like hyper-network to represent data instances as a compact representation vector. With instance-specific representation vector and instance-agnostic ANR parameters, the target signals are well reconstructed as a continuous function. We further address aliasing artifacts with variational coordinates when obtaining the super-resolution inference results. Extensive experimentation across four datasets showcases the notable efficacy of our ANR method, e.g. enhancing the PSNR value from 37.95dB to 47.25dB on the CelebA dataset. Code is released at https://github.com/Roninton/ANR.

Haoyu Chen, Zhihua Wang, Yang Yang et al.

Most well-established and widely used color difference (CD) metrics are handcrafted and subject-calibrated against uniformly colored patches, which do not generalize well to photographic images characterized by natural scene complexities. Constructing CD formulae for photographic images is still an active research topic in imaging/illumination, vision science, and color science communities. In this paper, we aim to learn a deep CD metric for photographic images with four desirable properties. First, it well aligns with the observations in vision science that color and form are linked inextricably in visual cortical processing. Second, it is a proper metric in the mathematical sense. Third, it computes accurate CDs between photographic images, differing mainly in color appearances. Fourth, it is robust to mild geometric distortions (e.g., translation or due to parallax), which are often present in photographic images of the same scene captured by different digital cameras. We show that all these properties can be satisfied at once by learning a multi-scale autoregressive normalizing flow for feature transform, followed by the Euclidean distance which is linearly proportional to the human perceptual CD. Quantitative and qualitative experiments on the large-scale SPCD dataset demonstrate the promise of the learned CD metric.

Anpeng Wu, Kun Kuang, Ruoxuan Xiong et al.

The advent of the big data era brought new opportunities and challenges to draw treatment effect in data fusion, that is, a mixed dataset collected from multiple sources (each source with an independent treatment assignment mechanism). Due to possibly omitted source labels and unmeasured confounders, traditional methods cannot estimate individual treatment assignment probability and infer treatment effect effectively. Therefore, we propose to reconstruct the source label and model it as a Group Instrumental Variable (GIV) to implement IV-based Regression for treatment effect estimation. In this paper, we conceptualize this line of thought and develop a unified framework (Meta-EM) to (1) map the raw data into a representation space to construct Linear Mixed Models for the assigned treatment variable; (2) estimate the distribution differences and model the GIV for the different treatment assignment mechanisms; and (3) adopt an alternating training strategy to iteratively optimize the representations and the joint distribution to model GIV for IV regression. Empirical results demonstrate the advantages of our Meta-EM compared with state-of-the-art methods.

Qi Tian, Kun Kuang, Kelu Jiang et al.

The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used to train their models. Therefore, it's important and necessary to develop a method or tool to prevent unauthorized data exploitation. In this paper, we propose ConfounderGAN, a generative adversarial network (GAN) that can make personal image data unlearnable to protect the data privacy of its owners. Specifically, the noise produced by the generator for each image has the confounder property. It can build spurious correlations between images and labels, so that the model cannot learn the correct mapping from images to labels in this noise-added dataset. Meanwhile, the discriminator is used to ensure that the generated noise is small and imperceptible, thereby remaining the normal utility of the encrypted image for humans. The experiments are conducted in six image classification datasets, consisting of three natural object datasets and three medical datasets. The results demonstrate that our method not only outperforms state-of-the-art methods in standard settings, but can also be applied to fast encryption scenarios. Moreover, we show a series of transferability and stability experiments to further illustrate the effectiveness and superiority of our method.

Minghao Zou, Gen Liu, Guanghui Yue et al.

The rapid advancement of generative models has led to a growing volume of AI-generated videos, making the automatic quality assessment of such videos increasingly important. Existing AI-generated content video quality assessment (AIGC-VQA) methods typically estimate visual quality by analyzing each video independently, ignoring potential relationships among videos. In this work, we revisit AIGC-VQA from an inter-video perspective and formulate it as a reference-aware evaluation problem. Through this formulation, quality assessment is guided not only by intrinsic video characteristics but also by comparisons with related videos, which is more consistent with human perception. To validate its effectiveness, we propose Reference-aware Video Quality Assessment (RefVQA), which utilizes a query-centered reference graph to organize semantically related samples and performs graph-guided difference aggregation from the reference nodes to the query node. Experiments on existing datasets demonstrate that our proposed RefVQA outperforms state-of-the-art methods across multiple quality dimensions, with strong generalization ability validated by cross-dataset evaluation. These results highlight the effectiveness of the proposed reference-based formulation and suggest its potential to advance AIGC-VQA.

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.

Yingjie Zhou, Zicheng Zhang, Wei Sun et al.

In the realm of media technology, digital humans have gained prominence due to rapid advancements in computer technology. However, the manual modeling and control required for the majority of digital humans pose significant obstacles to efficient development. The speech-driven methods offer a novel avenue for manipulating the mouth shape and expressions of digital humans. Despite the proliferation of driving methods, the quality of many generated talking head (TH) videos remains a concern, impacting user visual experiences. To tackle this issue, this paper introduces the Talking Head Quality Assessment (THQA) database, featuring 800 TH videos generated through 8 diverse speech-driven methods. Extensive experiments affirm the THQA database's richness in character and speech features. Subsequent subjective quality assessment experiments analyze correlations between scoring results and speech-driven methods, ages, and genders. In addition, experimental results show that mainstream image and video quality assessment methods have limitations for the THQA database, underscoring the imperative for further research to enhance TH video quality assessment. The THQA database is publicly accessible at https://github.com/zyj-2000/THQA.

Kehua Feng, Keyan Ding, Hongzhi Tan et al.

Reliable evaluation of large language models (LLMs) is impeded by two key challenges: objective metrics often fail to reflect human perception of natural language, and exhaustive human labeling is prohibitively expensive. Here, we propose a sample-efficient human evaluation method for LLMs based on the principle of MAximum Discrepancy (MAD) Competition. Our method automatically and adaptively selects a compact set of input instructions that maximize semantic discrepancy between pairs of LLM responses. Human evaluators then perform three-alternative forced choices on these paired responses, which are aggregated into a global ranking using Elo rating. We apply our approach to compare eight widely used LLMs across four tasks: scientific knowledge understanding, mathematical reasoning, creative and functional writing, and code generation and explanation. Experimental results show that our sample-efficient evaluation method recovers "gold-standard" model rankings with a handful of MAD-selected instructions, reveals respective strengths and weaknesses of each LLM, and offers nuanced insights to guide future LLM development. Code is available at https://github.com/weiji-Feng/MAD-Eval .

Yixiao Li, Xin Li, Chris Wei Zhou et al.

This paper presents the ISRGC-Q Challenge, built upon the Image Super-Resolution Generated Content Quality Assessment (ISRGen-QA) dataset, and organized as part of the Visual Quality Assessment (VQualA) Competition at the ICCV 2025 Workshops. Unlike existing Super-Resolution Image Quality Assessment (SR-IQA) datasets, ISRGen-QA places a greater emphasis on SR images generated by the latest generative approaches, including Generative Adversarial Networks (GANs) and diffusion models. The primary goal of this challenge is to analyze the unique artifacts introduced by modern super-resolution techniques and to evaluate their perceptual quality effectively. A total of 108 participants registered for the challenge, with 4 teams submitting valid solutions and fact sheets for the final testing phase. These submissions demonstrated state-of-the-art (SOTA) performance on the ISRGen-QA dataset. The project is publicly available at: https://github.com/Lighting-YXLI/ISRGen-QA.

Shunyang Luo, Peibei Cao, Zhihui Zhu et al.

Reward models (RMs) are central to aligning large language models, yet their practical effectiveness hinges on generalization to unseen prompts and shifting distributions. Most existing RM evaluations rely on static, pre-annotated preference datasets, which provide limited coverage and often fail to faithfully assess generalization in open-world settings. We introduce Pairwise Maximum Discrepancy Competition (PMDC), a dynamic and annotation-efficient framework for evaluating RM generalization using a large, unlabeled, open-domain prompt pool. PMDC actively selects prompt--response pairs that maximize disagreement between two RMs, yielding a compact set of highly contentious test cases. These cases are adjudicated by an oracle, and the resulting outcomes are aggregated via a Bradley--Terry model to produce a global ranking and pairwise win-rate landscape of RMs. We apply PMDC to re-evaluate 10 representative RMs and observe substantial rank reshuffling compared with conventional benchmarks. Qualitative analyses further uncover systematic generalization failures, providing valuable insights for improving reward modeling.

Ruijie Yang, Yan Zhu, Peiyao Fu et al.

Automatic speech recognition (ASR) is a critical interface for human-AI interaction in gastrointestinal endoscopy, yet its reliability in real-world clinical settings is limited by domain-specific terminology and complex acoustic conditions. Here, we present EndoASR, a domain-adapted ASR system designed for real-time deployment in endoscopic workflows. We develop a two-stage adaptation strategy based on synthetic endoscopy reports, targeting domain-specific language modeling and noise robustness. In retrospective evaluation across six endoscopists, EndoASR substantially improves both transcription accuracy and clinical usability, reducing character error rate (CER) from 20.52% to 14.14% and increasing medical term accuracy (Med ACC) from 54.30% to 87.59%. In a prospective multi-center study spanning five independent endoscopy centers, EndoASR demonstrates consistent generalization under heterogeneous real-world conditions. Compared with the baseline Paraformer model, CER is reduced from 16.20% to 14.97%, while Med ACC is improved from 61.63% to 84.16%, confirming its robustness in practical deployment scenarios. Notably, EndoASR achieves a real-time factor (RTF) of 0.005, significantly faster than Whisper-large-v3 (RTF 0.055), while maintaining a compact model size of 220M parameters, enabling efficient edge deployment. Furthermore, integration with large language models demonstrates that improved ASR quality directly enhances downstream structured information extraction and clinician-AI interaction. These results demonstrate that domain-adapted ASR can serve as a reliable interface for human-AI teaming in gastrointestinal endoscopy, with consistent performance validated across multi-center real-world clinical settings.

Ruijie Yang, Yan Zhu, Peiyao Fu et al.

Determining the necessity of resecting malignant polyps during colonoscopy screen is crucial for patient outcomes, yet challenging due to the time-consuming and costly nature of histopathology examination. While deep learning-based classification models have shown promise in achieving optical biopsy with endoscopic images, they often suffer from a lack of explainability. To overcome this limitation, we introduce EndoFinder, a content-based image retrieval framework to find the 'digital twin' polyp in the reference database given a newly detected polyp. The clinical semantics of the new polyp can be inferred referring to the matched ones. EndoFinder pioneers a polyp-aware image encoder that is pre-trained on a large polyp dataset in a self-supervised way, merging masked image modeling with contrastive learning. This results in a generic embedding space ready for different downstream clinical tasks based on image retrieval. We validate the framework on polyp re-identification and optical biopsy tasks, with extensive experiments demonstrating that EndoFinder not only achieves explainable diagnostics but also matches the performance of supervised classification models. EndoFinder's reliance on image retrieval has the potential to support diverse downstream decision-making tasks during real-time colonoscopy procedures.

Jia Yu, Yan Zhu, Peiyao Fu et al.

Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, restricting the data available for developing reliable artificial intelligence (AI) models and training novice clinicians. Here we present EndoRare, a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image. By leveraging language-guided concept disentanglement, EndoRare separates pathognomonic lesion features from non-diagnostic attributes, encoding the former into a learnable prototype embedding while varying the latter to ensure diversity. We validated the framework across four rare pathologies (calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome). Synthetic images were judged clinically plausible by experts and, when used for data augmentation, significantly enhanced downstream AI classifiers, improving the true positive rate at low false-positive rates. Crucially, a blinded reader study demonstrated that novice endoscopists exposed to EndoRare-generated cases achieved a 0.400 increase in recall and a 0.267 increase in precision. These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.

Chao Huang, Penfei Wei, Wei Wang et al.

Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large-scale annotations or task-specific training procedures, severely limiting their rapid deployment to novel scenes. We observe that intermediate-layer features of pre-trained multimodal large language models (MLLMs) already encode rich anomaly semantics, yet existing approaches rely on the language output pathway and fail to exploit the geometric discriminability latent in these representations. Based on this finding, we propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere, unleashing latent discriminability through principled geometric reasoning rather than learning new representations. Specifically, SphereVAD first applies Frechet mean centering to unfold feature distributions and eliminate domain biases, then employs Holistic Scene Attention (HSA) to reinforce feature consistency using cross-video priors, and finally performs vMF-guided Spherical Geodesic Pulling (SGP) to align ambiguous segments with directional prototypes on the spherical manifold. This training-free pipeline requires only minimal synthetic images for calibration. SphereVAD establishes new state-of-the-art results among training-free approaches on three major benchmarks and remains competitive with fully supervised baselines. Code will be available upon acceptance.

Jian Zou, Xiaoyu Xu, Zhihua Wang et al.

Learning-based video quality assessment (VQA) has advanced rapidly, yet progress is increasingly constrained by a disconnect between model design and dataset curation. Model-centric approaches often iterate on fixed benchmarks, while data-centric efforts collect new human labels without systematically targeting the weaknesses of existing VQA models. Here, we describe MDS-VQA, a model-informed data selection mechanism for curating unlabeled videos that are both difficult for the base VQA model and diverse in content. Difficulty is estimated by a failure predictor trained with a ranking objective, and diversity is measured using deep semantic video features, with a greedy procedure balancing the two under a constrained labeling budget. Experiments across multiple VQA datasets and models demonstrate that MDS-VQA identifies diverse, challenging samples that are particularly informative for active fine-tuning. With only a 5% selected subset per target domain, the fine-tuned model improves mean SRCC from 0.651 to 0.722 and achieves the top gMAD rank, indicating strong adaptation and generalization.

Jiebin Yan, Chenyu Tu, Weixia Zhang et al.

This paper presents a comprehensive review of the NITRE 2026 Efficient Low Light Image Enhancement (E-LLIE) Challenge, highlighting the proposed solutions and final outcomes. This challenge focuses on mobile image enhancement under low-light conditions, aiming to design lightweight networks that improve enhancement quality while ensuring practical deployability under limited computational resources. A total of 207 participants registered, 27 teams submitted valid entries, and 17 teams ultimately provided valid factsheet. Based on these submissions, this paper provides a systematic evaluation of recent methods for E-LLIE, offering a comprehensive overview of state-of-the-art progress and demonstrating significant improvements in both performance and efficiency.

Hanyu Liu, Yunsheng Ma, Jiaxin Huang et al.

This paper presents RoboMatch, a novel unified teleoperation platform for mobile manipulation with an auto-matching network architecture, designed to tackle long-horizon tasks in dynamic environments. Our system enhances teleoperation performance, data collection efficiency, task accuracy, and operational stability. The core of RoboMatch is a cockpit-style control interface that enables synchronous operation of the mobile base and dual arms, significantly improving control precision and data collection. Moreover, we introduce the Proprioceptive-Visual Enhanced Diffusion Policy (PVE-DP), which leverages Discrete Wavelet Transform (DWT) for multi-scale visual feature extraction and integrates high-precision IMUs at the end-effector to enrich proprioceptive feedback, substantially boosting fine manipulation performance. Furthermore, we propose an Auto-Matching Network (AMN) architecture that decomposes long-horizon tasks into logical sequences and dynamically assigns lightweight pre-trained models for distributed inference. Experimental results demonstrate that our approach improves data collection efficiency by over 20%, increases task success rates by 20-30% with PVE-DP, and enhances long-horizon inference performance by approximately 40% with AMN, offering a robust solution for complex manipulation tasks. Project website: https://robomatch.github.io

Jialong Guo, Ke liu, Jiangchao Yao et al.

Neural Representations for Videos (NeRV) has emerged as a promising implicit neural representation (INR) approach for video analysis, which represents videos as neural networks with frame indexes as inputs. However, NeRV-based methods are time-consuming when adapting to a large number of diverse videos, as each video requires a separate NeRV model to be trained from scratch. In addition, NeRV-based methods spatially require generating a high-dimension signal (i.e., an entire image) from the input of a low-dimension timestamp, and a video typically consists of tens of frames temporally that have a minor change between adjacent frames. To improve the efficiency of video representation, we propose Meta Neural Representations for Videos, named MetaNeRV, a novel framework for fast NeRV representation for unseen videos. MetaNeRV leverages a meta-learning framework to learn an optimal parameter initialization, which serves as a good starting point for adapting to new videos. To address the unique spatial and temporal characteristics of video modality, we further introduce spatial-temporal guidance to improve the representation capabilities of MetaNeRV. Specifically, the spatial guidance with a multi-resolution loss aims to capture the information from different resolution stages, and the temporal guidance with an effective progressive learning strategy could gradually refine the number of fitted frames during the meta-learning process. Extensive experiments conducted on multiple datasets demonstrate the superiority of MetaNeRV for video representations and video compression.

Yemin Yu, Luotian Yuan, Ying Wei et al.

Machine learning-assisted retrosynthesis prediction models have been gaining widespread adoption, though their performances oftentimes degrade significantly when deployed in real-world applications embracing out-of-distribution (OOD) molecules or reactions. Despite steady progress on standard benchmarks, our understanding of existing retrosynthesis prediction models under the premise of distribution shifts remains stagnant. To this end, we first formally sort out two types of distribution shifts in retrosynthesis prediction and construct two groups of benchmark datasets. Next, through comprehensive experiments, we systematically compare state-of-the-art retrosynthesis prediction models on the two groups of benchmarks, revealing the limitations of previous in-distribution evaluation and re-examining the advantages of each model. More remarkably, we are motivated by the above empirical insights to propose two model-agnostic techniques that can improve the OOD generalization of arbitrary off-the-shelf retrosynthesis prediction algorithms. Our preliminary experiments show their high potential with an average performance improvement of 4.6%, and the established benchmarks serve as a foothold for further retrosynthesis prediction research towards OOD generalization.

Shuai Niu, Jing Ma, Hongzhan Lin et al.

Interpretation is critical for disease diagnosis, but existing models struggle to balance predictive accuracy with human-understandable rationales. While large language models (LLMs) offer strong reasoning abilities, their clinical use is limited by high computational costs and restricted multimodal reasoning ability. Small language models (SLMs) are efficient but lack advanced reasoning for integrating multimodal medical data. In addition, both LLMs and SLMs lack domain knowledge for trustworthy reasoning. Therefore, we propose ClinRaGen, enhancing SLMs by leveraging LLM-derived reasoning ability via rationale distillation and domain knowledge injection for trustworthy multimodal rationale generation. Key innovations include a sequential rationale distillation framework that equips SLMs with LLM-comparable multimodal reasoning abilities, and a knowledge-augmented attention mechanism that jointly unifies multimodal representation from time series and textual data in the same encoding space, enabling it to be naturally interpreted by SLMs while incorporating domain knowledge for reliable rationale generation. Experiments on real-world medical datasets show that ClinRaGen achieves state-of-the-art performance in disease diagnosis and rationale generation, demonstrating the effectiveness of combining LLM-driven reasoning with knowledge augmentation for improved interpretability.

Siyuan Zhou, Hejun Wang, Hu Cheng et al.

We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2 million videos across 153,810 dynamic 3D scenes, covering 71 basic physical phenomena in mechanics, optics, fluid dynamics, and magnetism. Distinct from previous works, our scenes feature multiobject interactions against complex backgrounds, with comprehensive ground-truth annotations including 3D geometry, semantics, dynamic motion, physical properties, and text descriptions. We demonstrate PhysInOne's efficacy across four emerging applications: physics-aware video generation, long-/short-term future frame prediction, physical property estimation, and motion transfer. Experiments show that fine-tuning foundation models on PhysInOne significantly enhances physical plausibility, while also exposing critical gaps in modeling complex physical dynamics and estimating intrinsic properties. As the largest dataset of its kind, orders of magnitude beyond prior works, PhysInOne establishes a new benchmark for advancing physics-grounded world models in generation, simulation, and embodied AI.

Jia Yu, Yan Zhu, Peiyao Fu et al.

Colorectal cancer (CRC) is a significant global health concern, and early detection through screening plays a critical role in reducing mortality. While deep learning models have shown promise in improving polyp detection, classification, and segmentation, their generalization across diverse clinical environments, particularly with out-of-distribution (OOD) data, remains a challenge. Multi-center datasets like PolypGen have been developed to address these issues, but their collection is costly and time-consuming. Traditional data augmentation techniques provide limited variability, failing to capture the complexity of medical images. Diffusion models have emerged as a promising solution for generating synthetic polyp images, but the image generation process in current models mainly relies on segmentation masks as the condition, limiting their ability to capture the full clinical context. To overcome these limitations, we propose a Progressive Spectrum Diffusion Model (PSDM) that integrates diverse clinical annotations-such as segmentation masks, bounding boxes, and colonoscopy reports-by transforming them into compositional prompts. These prompts are organized into coarse and fine components, allowing the model to capture both broad spatial structures and fine details, generating clinically accurate synthetic images. By augmenting training data with PSDM-generated samples, our model significantly improves polyp detection, classification, and segmentation. For instance, on the PolypGen dataset, PSDM increases the F1 score by 2.12% and the mean average precision by 3.09%, demonstrating superior performance in OOD scenarios and enhanced generalization.

Yili He, Yan Zhu, Peiyao Fu et al.

Pre-training on image-text colonoscopy records offers substantial potential for improving endoscopic image analysis, but faces challenges including non-informative background images, complex medical terminology, and ambiguous multi-lesion descriptions. We introduce Endo-CLIP, a novel self-supervised framework that enhances Contrastive Language-Image Pre-training (CLIP) for this domain. Endo-CLIP's three-stage framework--cleansing, attunement, and unification--addresses these challenges by (1) removing background frames, (2) leveraging large language models to extract clinical attributes for fine-grained contrastive learning, and (3) employing patient-level cross-attention to resolve multi-polyp ambiguities. Extensive experiments demonstrate that Endo-CLIP significantly outperforms state-of-the-art pre-training methods in zero-shot and few-shot polyp detection and classification, paving the way for more accurate and clinically relevant endoscopic analysis.

Zhihua Wang, Yu Long, Qinghua Lin et al.

Deep neural networks (DNNs) have recently become the leading method for low-light image enhancement (LLIE). However, despite significant progress, their outputs may still exhibit issues such as amplified noise, incorrect white balance, or unnatural enhancements when deployed in real world applications. A key challenge is the lack of diverse, large scale training data that captures the complexities of low-light conditions and imaging pipelines. In this paper, we propose a novel image signal processing (ISP) driven data synthesis pipeline that addresses these challenges by generating unlimited paired training data. Specifically, our pipeline begins with easily collected high-quality normal-light images, which are first unprocessed into the RAW format using a reverse ISP. We then synthesize low-light degradations directly in the RAW domain. The resulting data is subsequently processed through a series of ISP stages, including white balance adjustment, color space conversion, tone mapping, and gamma correction, with controlled variations introduced at each stage. This broadens the degradation space and enhances the diversity of the training data, enabling the generated data to capture a wide range of degradations and the complexities inherent in the ISP pipeline. To demonstrate the effectiveness of our synthetic pipeline, we conduct extensive experiments using a vanilla UNet model consisting solely of convolutional layers, group normalization, GeLU activation, and convolutional block attention modules (CBAMs). Extensive testing across multiple datasets reveals that the vanilla UNet model trained with our data synthesis pipeline delivers high fidelity, visually appealing enhancement results, surpassing state-of-the-art (SOTA) methods both quantitatively and qualitatively.

Shuai Niu, Jing Ma, Hongzhan Lin et al.

Large language models (LLMs) have shown remarkable performance in vision-language tasks, but their application in the medical field remains underexplored, particularly for integrating structured time series data with unstructured clinical notes. In clinical practice, dynamic time series data, such as lab test results, capture critical temporal patterns, while clinical notes provide rich semantic context. Merging these modalities is challenging due to the inherent differences between continuous signals and discrete text. To bridge this gap, we introduce ProMedTS, a novel self-supervised multimodal framework that employs prompt-guided learning to unify these heterogeneous data types. Our approach leverages lightweight anomaly detection to generate anomaly captions that serve as prompts, guiding the encoding of raw time series data into informative prompt embeddings. These prompt embeddings are aligned with textual representations in a shared latent space, preserving fine-grained temporal nuances alongside semantic insights. Furthermore, our framework incorporates tailored self-supervised objectives to enhance both intra- and inter-modal alignment. We evaluate ProMedTS on disease diagnosis tasks using real-world datasets, and the results demonstrate that our method consistently outperforms state-of-the-art approaches.

Qingyong Hu, Bo Yang, Linhai Xie et al.

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches. Moreover, extensive experiments on five large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, NPM3D and S3DIS, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.

Zhihua Wang, Zhi-Ri Tang, Jianguo Zhang et al.

Nowadays, most existing blind image quality assessment (BIQA) models 1) are developed for synthetically-distorted images and often generalize poorly to authentic ones; 2) heavily rely on human ratings, which are prohibitively labor-expensive to collect. Here, we propose an $opinion$-$free$ BIQA method that learns from synthetically-distorted images and multiple agents to assess the perceptual quality of authentically-distorted ones captured in the wild without relying on human labels. Specifically, we first assemble a large number of image pairs from synthetically-distorted images and use a set of full-reference image quality assessment (FR-IQA) models to assign pseudo-binary labels of each pair indicating which image has higher quality as the supervisory signal. We then train a convolutional neural network (CNN)-based BIQA model to rank the perceptual quality, optimized for consistency with the binary labels. Since there exists domain shift between the synthetically- and authentically-distorted images, an unsupervised domain adaptation (UDA) module is introduced to alleviate this issue. Extensive experiments demonstrate the effectiveness of our proposed $opinion$-$free$ BIQA model, yielding state-of-the-art performance in terms of correlation with human opinion scores, as well as gMAD competition. Codes will be made publicly available upon acceptance.

Zhihua Wang, Dingquan Li, Kede Ma

Ensemble methods are generally regarded to be better than a single model if the base learners are deemed to be "accurate" and "diverse." Here we investigate a semi-supervised ensemble learning strategy to produce generalizable blind image quality assessment models. We train a multi-head convolutional network for quality prediction by maximizing the accuracy of the ensemble (as well as the base learners) on labeled data, and the disagreement (i.e., diversity) among them on unlabeled data, both implemented by the fidelity loss. We conduct extensive experiments to demonstrate the advantages of employing unlabeled data for BIQA, especially in model generalization and failure identification.

Zhihua Wang, Haotao Wang, Tianlong Chen et al.

Recently, the group maximum differentiation competition (gMAD) has been used to improve blind image quality assessment (BIQA) models, with the help of full-reference metrics. When applying this type of approach to troubleshoot "best-performing" BIQA models in the wild, we are faced with a practical challenge: it is highly nontrivial to obtain stronger competing models for efficient failure-spotting. Inspired by recent findings that difficult samples of deep models may be exposed through network pruning, we construct a set of "self-competitors," as random ensembles of pruned versions of the target model to be improved. Diverse failures can then be efficiently identified via self-gMAD competition. Next, we fine-tune both the target and its pruned variants on the human-rated gMAD set. This allows all models to learn from their respective failures, preparing themselves for the next round of self-gMAD competition. Experimental results demonstrate that our method efficiently troubleshoots BIQA models in the wild with improved generalizability.

Shaofeng Zou, Mingzhu Long, Xuyang Wang et al.

The quality of images captured by wireless capsule endoscopy (WCE) is key for doctors to diagnose diseases of gastrointestinal (GI) tract. However, there exist many low-quality endoscopic images due to the limited illumination and complex environment in GI tract. After an enhancement process, the severe noise become an unacceptable problem. The noise varies with different cameras, GI tract environments and image enhancement. And the noise model is hard to be obtained. This paper proposes a convolutional blind denoising network for endoscopic images. We apply Deep Image Prior (DIP) method to reconstruct a clean image iteratively using a noisy image without a specific noise model and ground truth. Then we design a blind image quality assessment network based on MobileNet to estimate the quality of the reconstructed images. The estimated quality is used to stop the iterative operation in DIP method. The number of iterations is reduced about 36% by using transfer learning in our DIP process. Experimental results on endoscopic images and real-world noisy images demonstrate the superiority of our proposed method over the state-of-the-art methods in terms of visual quality and quantitative metrics.

Zhihua Wang, Kede Ma

The research in image quality assessment (IQA) has a long history, and significant progress has been made by leveraging recent advances in deep neural networks (DNNs). Despite high correlation numbers on existing IQA datasets, DNN-based models may be easily falsified in the group maximum differentiation (gMAD) competition with strong counterexamples being identified. Here we show that gMAD examples can be used to improve blind IQA (BIQA) methods. Specifically, we first pre-train a DNN-based BIQA model using multiple noisy annotators, and fine-tune it on multiple subject-rated databases of synthetically distorted images, resulting in a top-performing baseline model. We then seek pairs of images by comparing the baseline model with a set of full-reference IQA methods in gMAD. The resulting gMAD examples are most likely to reveal the relative weaknesses of the baseline, and suggest potential ways for refinement. We query ground truth quality annotations for the selected images in a well controlled laboratory environment, and further fine-tune the baseline on the combination of human-rated images from gMAD and existing databases. This process may be iterated, enabling active and progressive fine-tuning from gMAD examples for BIQA. We demonstrate the feasibility of our active learning scheme on a large-scale unlabeled image set, and show that the fine-tuned method achieves improved generalizability in gMAD, without destroying performance on previously trained databases.

Qingyong Hu, Bo Yang, Linhai Xie et al.

We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.

Linhai Xie, Yishu Miao, Sen Wang et al.

Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of high variance when applied in complex real world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an agent to choose between high and low variance policies. The stochastic switch can be jointly trained with the original DDPG in the same framework. In this paper, we demonstrate the power of the framework in a navigation task, where the robot can dynamically choose to learn through exploration, or to use the output of a heuristic controller as guidance. Instead of starting from completely random moves, the navigation capability of a robot can be quickly bootstrapped by several simple independent controllers. The experimental results show that with the aid of stochastic guidance we are able to effectively and efficiently train DDPG navigation policies and achieve significantly better performance than state-of-the-art baselines models.

Zhihua Wang, Stefano Rosa, Yishu Miao et al.

Humans are able to make rich predictions about the future dynamics of physical objects from a glance. On the other hand, most existing computer vision approaches require strong assumptions about the underlying system, ad-hoc modeling, or annotated datasets, to carry out even simple predictions. To tackle this gap, we propose a new perspective on the problem of learning intuitive physics that is inspired by the spatial memory representation of objects and spaces in human brains, in particular the co-existence of egocentric and allocentric spatial representations. We present a generic framework that learns a layered representation of the physical world, using a cascade of invertible modules. In this framework, real images are first converted to a synthetic domain representation that reduces complexity arising from lighting and texture. Then, an allocentric viewpoint transformer removes viewpoint complexity by projecting images to a canonical view. Finally, a novel Recurrent Latent Variation Network (RLVN) architecture learns the dynamics of the objects interacting with the environment and predicts future motion, leveraging the availability of unlimited synthetic simulations. Predicted frames are then projected back to the original camera view and translated back to the real world domain. Experimental results show the ability of the framework to consistently and accurately predict several frames in the future and the ability to adapt to real images.

Zhihua Wang, Stefano Rosa, Bo Yang et al.

The ability to interact and understand the environment is a fundamental prerequisite for a wide range of applications from robotics to augmented reality. In particular, predicting how deformable objects will react to applied forces in real time is a significant challenge. This is further confounded by the fact that shape information about encountered objects in the real world is often impaired by occlusions, noise and missing regions e.g. a robot manipulating an object will only be able to observe a partial view of the entire solid. In this work we present a framework, 3D-PhysNet, which is able to predict how a three-dimensional solid will deform under an applied force using intuitive physics modelling. In particular, we propose a new method to encode the physical properties of the material and the applied force, enabling generalisation over materials. The key is to combine deep variational autoencoders with adversarial training, conditioned on the applied force and the material properties. We further propose a cascaded architecture that takes a single 2.5D depth view of the object and predicts its deformation. Training data is provided by a physics simulator. The network is fast enough to be used in real-time applications from partial views. Experimental results show the viability and the generalisation properties of the proposed architecture.

Zhihua Wang, Stefano Rosa, Linhai Xie et al.

Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots. We present a novel generative adversarial network (Defo-Net), able to predict body deformations under external forces from a single RGB-D image. The network is based on an invertible conditional Generative Adversarial Network (IcGAN) and is trained on a collection of different objects of interest generated by a physical finite element model simulator. Defo-Net inherits the generalisation properties of GANs. This means that the network is able to reconstruct the whole 3-D appearance of the object given a single depth view of the object and to generalise to unseen object configurations. Contrary to traditional finite element methods, our approach is fast enough to be used in real-time applications. We apply the network to the problem of safe and fast navigation of mobile robots carrying payloads over different obstacles and floor materials. Experimental results in real scenarios show how a robot equipped with an RGB-D camera can use the network to predict terrain deformations under different payload configurations and use this to avoid unsafe areas.

Rahman Attar, Xiang Xie, Zhihua Wang et al.

Examining and interpreting of a large number of wireless endoscopic images from the gastrointestinal tract is a tiresome task for physicians. A practical solution is to automatically construct a two dimensional representation of the gastrointestinal tract for easy inspection. However, little has been done on wireless endoscopic image stitching, let alone systematic investigation. The proposed new wireless endoscopic image stitching method consists of two main steps to improve the accuracy and efficiency of image registration. First, the keypoints are extracted by Principle Component Analysis and Scale Invariant Feature Transform (PCA-SIFT) algorithm and refined with Maximum Likelihood Estimation SAmple Consensus (MLESAC) outlier removal to find the most reliable keypoints. Second, the optimal transformation parameters obtained from first step are fed to the Normalised Mutual Information (NMI) algorithm as an initial solution. With modified Marquardt-Levenberg search strategy in a multiscale framework, the NMI can find the optimal transformation parameters in the shortest time. The proposed methodology has been tested on two different datasets - one with real wireless endoscopic images and another with images obtained from Micro-Ball (a new wireless cubic endoscopy system with six image sensors). The results have demonstrated the accuracy and robustness of the proposed methodology both visually and quantitatively.

Jiannan Zhao, Cheng Hu, Chun Zhang et al.

Sense and avoid capability enables insects to fly versatilely and robustly in dynamic complex environment. Their biological principles are so practical and efficient that inspired we human imitating them in our flying machines. In this paper, we studied a novel bio-inspired collision detector and its application on a quadcopter. The detector is inspired from LGMD neurons in the locusts, and modeled into an STM32F407 MCU. Compared to other collision detecting methods applied on quadcopters, we focused on enhancing the collision selectivity in a bio-inspired way that can considerably increase the computing efficiency during an obstacle detecting task even in complex dynamic environment. We designed the quadcopter's responding operation imminent collisions and tested this bio-inspired system in an indoor arena. The observed results from the experiments demonstrated that the LGMD collision detector is feasible to work as a vision module for the quadcopter's collision avoidance task.