Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Saturday 22 November

Computer Vision

Video4Edit: Viewing Image Editing as a Degenerate Temporal Process

We observe that recent advances in multimodal foundation models have propelled instruction-driven image generation and editing into a genuinely cross-modal, cooperative regime. Nevertheless, state-of-the-art editing pipelines remain costly: beyond training large diffusion/flow models, they require curating massive high-quality triplets of \{instruction, source image, edited image\} to cover diverse user intents. Moreover, the fidelity of visual replacements hinges on how precisely the instruction references the target semantics. We revisit this challenge through the lens of temporal modeling: if video can be regarded as a full temporal process, then image editing can be seen as a degenerate temporal process. This perspective allows us to transfer single-frame evolution priors from video pre-training, enabling a highly data-efficient fine-tuning regime. Empirically, our approach matches the performance of leading open-source baselines while using only about one percent of the supervision demanded by mainstream editing models.
Read the full abstract

All authors Xiaofan Li, Yanpeng Sun, Chenming Wu, Fan Duan, YuAn Wang, Weihao Bo, Yumeng Zhang, Dingkang Liang

Computer Vision

Predictive Representation Learning for Manipulation via Streaming Egocentric 3D Hand Forecasting

Learning embodied manipulation from egocentric human data offers a scalable path, reducing the cost of collecting robot-specific demonstrations. However, existing representation learning methods largely stop at perceptual understanding, such as extracting what a scene contains or what an action is. A capable embodied agent is more than understanding: it predicts the next motion. We propose that forecasting 3D human hand motion is one suitable pretraining task, as the representation jointly learns how to manipulate objects and how the motion will unfold next. Building on this hypothesis, we introduce SFHand, the first representation learning method via streaming egocentric 3D hand forecasting. SFHand learns by autoregressively predicting future 3D hand states, including hand type, 2D bounding box, 3D pose, and trajectory, from a continuous stream of video and language instructions. Its autoregressive architecture is equipped with an ROI-enhanced memory layer, capturing temporal context while focusing on salient hand-centric regions. To enable this research, we also introduce SFHand, the first open-source large-scale dataset pairing synchronized 3D hand poses with fine-grained language instructions (247K clips, 3.95M frames). Transferred to downstream embodied control, the learned representation shows state-of-the-art performance on both simulation and real-world manipulation benchmarks, improving success rate by up to 13.4%. Our method also achieves leading 3D hand forecasting accuracy, with 35.8% lower ADE than baseline methods. These results suggest that forecasting hand motion is a better pretraining task for representation learning in embodied manipulation. Projec page: https://ruicongliu.github.io/sfhand/.
Read the full abstract

All authors Ruicong Liu, Yifei Huang, Liangyang Ouyang, Caixin Kang, Yoichi Sato

Computer Vision

Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such behavior undermines fairness and distorts the intended alignment between vision and language. Recent post-hoc approaches attempt to mitigate bias by replacing the most attribute-correlated embedding coordinates with neutral values. However, our systematic analysis reveals three critical limitations of this coordinate-wise approach: feature entanglement, poor cross-dataset generalization, and incomplete bias removal. We find that bias is not localized to a few coordinates but is instead distributed across a few linear subspaces. To address these limitations, we propose $\textbf{S}$ubspace $\textbf{P}$rojection $\textbf{D}$ebiasing ($\textbf{SPD}$), a geometrically principled framework that identifies and removes the entire subspace of linearly decodable bias while reinserting a neutral mean component to preserve semantic fidelity. Extensive experiments across zero-shot classification, text-to-image retrieval, and image generation validate the effectiveness of SPD: our method achieves more robust debiasing with an average improvement of $18.5\%$ across four fairness metrics, while maintaining minimal loss in task performance compared to the best debiasing baseline.
Read the full abstract

All authors Dachuan Zhao, Weiyue Li, Zhenda Shen, Yushu Qiu, Bowen Xu, Haoyu Chen, Yongchao Chen

Computer Vision

VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging

While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visual information. Unlike humans who naturally bridge details and high-level concepts, models tend to treat these elements in isolation. Prevailing evaluation protocols often decouple low-level perception from high-level reasoning, overlooking their semantic and causal dependencies, which yields non-diagnostic results and obscures performance bottlenecks. We present VCU-Bridge, a framework that operationalizes a human-like hierarchy of visual connotation understanding: multi-level reasoning that advances from foundational perception through semantic bridging to abstract connotation, with an explicit evidence-to-inference trace from concrete cues to abstract conclusions. Building on this framework, we construct HVCU-Bench, a benchmark for hierarchical visual connotation understanding with explicit, level-wise diagnostics. Comprehensive experiments demonstrate a consistent decline in performance as reasoning progresses to higher levels. We further develop a data generation pipeline for instruction tuning guided by Monte Carlo Tree Search (MCTS) and show that strengthening low-level capabilities yields measurable gains at higher levels. Interestingly, it not only improves on HVCU-Bench but also brings benefits on general benchmarks (average +2.53%), especially with substantial gains on MMStar (+7.26%), demonstrating the significance of the hierarchical thinking pattern and its effectiveness in enhancing MLLM capabilities. The project page is at https://vcu-bridge.github.io .
Read the full abstract

All authors Ming Zhong, Yuanlei Wang, Liuzhou Zhang, Ruichuan An, Renrui Zhang, Hao Liang, Ming Lu, Ying Shen, Wentao Zhang

Computer Vision

MVS-TTA: Test-Time Adaptation for Multi-View Stereo via Meta-Auxiliary Learning

Recent learning-based multi-view stereo (MVS) methods are data-driven and have achieved remarkable progress due to large-scale training data and advanced architectures. However, their generalization remains sub-optimal due to fixed model parameters trained on limited training data distributions. In contrast, optimization-based methods enable scene-specific adaptation but lack scalability and require costly per-scene optimization. In this paper, we propose MVS-TTA, an efficient test-time adaptation (TTA) framework that enhances the adaptability of learning-based MVS methods by bridging these two paradigms. Specifically, MVS-TTA employs a self-supervised, cross-view consistency loss as an auxiliary task to guide inference-time adaptation. We introduce a meta-auxiliary learning strategy to train the model to benefit from auxiliary-task-based updates explicitly. Our framework is model-agnostic and can be applied to a wide range of MVS methods with minimal architectural changes. Extensive experiments on standard datasets (DTU, BlendedMVS) and a challenging cross-dataset generalization setting demonstrate that MVS-TTA consistently improves performance, even when applied to state-of-the-art MVS models. To our knowledge, this is the first attempt to integrate optimization-based test-time adaptation into learning-based MVS using meta-learning. The code will be available at https://github.com/mart87987-svg/MVS-TTA.
Read the full abstract

All authors Hannuo Zhang, Zhixiang Chi, Yang Wang, Xinxin Zuo

Computer Vision

PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures

Zero-Shot Anomaly Detection (ZSAD) aims to identify and localize anomalous regions in images of unseen object classes. While recent methods based on vision-language models like CLIP show promise, their performance is constrained by existing prompt engineering strategies. Current approaches, whether relying on single fixed, learnable, or dense dynamic prompts, suffer from a representational bottleneck and are prone to overfitting on auxiliary data, failing to generalize to the complexity and diversity of unseen anomalies. To overcome these limitations, we propose $\mathtt{PromptMoE}$. Our core insight is that robust ZSAD requires a compositional approach to prompt learning. Instead of learning monolithic prompts, $\mathtt{PromptMoE}$ learns a pool of expert prompts, which serve as a basis set of composable semantic primitives, and a visually-guided Mixture-of-Experts (MoE) mechanism to dynamically combine them for each instance. Our framework materializes this concept through a Visually-Guided Mixture of Prompt (VGMoP) that employs an image-gated sparse MoE to aggregate diverse normal and abnormal expert state prompts, generating semantically rich textual representations with strong generalization. Extensive experiments across 15 datasets in industrial and medical domains demonstrate the effectiveness and state-of-the-art performance of $\mathtt{PromptMoE}$.
Read the full abstract

All authors Yuheng Shao, Lizhang Wang, Changhao Li, Peixian Chen, Qinyuan Liu

Computer Vision

Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training

We present Muskie, a native multi-view vision backbone designed for 3D vision tasks. Unlike existing models, which are frame-wise and exhibit limited multi-view consistency, Muskie is designed to process multiple views simultaneously and introduce multi-view consistency in pre-training stage. Muskie is trained to reconstruct heavily masked content in one view by finding and utilizing geometric correspondences from other views. Through this pretext task and our proposed aggressive masking strategy, the model implicitly to learn view-invariant features and develop strong geometric understanding without any 3D supervision. Compared with state-of-the-art frame-wise backbones such as DINO, Muskie achieves higher multi-view correspondence accuracy. Furthermore, we demonstrate that using Muskie as a backbone consistently enhances performance on downstream 3D tasks, including camera pose estimation and pointmap reconstruction. Codes are publicly available at https://leo-frank.github.io/Muskie/
Read the full abstract

All authors Wenyu Li, Sidun Liu, Peng Qiao, Yong Dou, Tongrui Hu

Computer Vision

AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens

Modern transformer architectures achieve remarkable performance across tasks and domains but remain rigid in how they allocate computation at inference time. Real-world deployment often requires models to adapt to diverse hardware and latency constraints, yet most approaches to dynamic computation focus on a single axis – such as reducing the number of tokens. We present a novel capability: AdaPerceiver, the first transformer architecture with unified adaptivity across depth, width, and tokens within a single model. We propose an architecture that supports adaptivity along these axes. We couple this with an efficient joint training regime that ensures the model maintains performance across its various configurations. We evaluate AdaPerceiver on image classification, semantic segmentation, and depth estimation tasks. On image classification, AdaPerceiver expands the accuracy-throughput Pareto front. It achieves 85.4% accuracy while yielding 36% higher throughput than FlexiViT-L. On dense prediction, AdaPerceiver matches ViT-H/14 while having $\sim$26x fewer encoder FLOPs (floating-point operations) on semantic segmentation and depth estimation. Finally, we show how AdaPerceiver equipped with a policy can maintain ImageNet1K accuracy ($\pm0.1$ percentage points) while reducing FLOPs by $24-33$%.
Read the full abstract

All authors Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiruvathukal, Yung-Hsiang Lu, James C. Davis

Computer Vision

Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learning

The proliferation of videos generated by diffusion models has raised increasing concerns about information security, highlighting the urgent need for reliable detection of synthetic media. Existing methods primarily focus on image-level forgery detection, leaving generic video-level forgery detection largely underexplored. To advance video forensics, we propose a consolidated multimodal detection algorithm, named MM-Det++, specifically designed for detecting diffusion-generated videos. Our approach consists of two innovative branches and a Unified Multimodal Learning (UML) module. Specifically, the Spatio-Temporal (ST) branch employs a novel Frame-Centric Vision Transformer (FC-ViT) to aggregate spatio-temporal information for detecting diffusion-generated videos, where the FC-tokens enable the capture of holistic forgery traces from each video frame. In parallel, the Multimodal (MM) branch adopts a learnable reasoning paradigm to acquire Multimodal Forgery Representation (MFR) by harnessing the powerful comprehension and reasoning capabilities of Multimodal Large Language Models (MLLMs), which discerns the forgery traces from a flexible semantic perspective. To integrate multimodal representations into a coherent space, a UML module is introduced to consolidate the generalization ability of MM-Det++. In addition, we also establish a large-scale and comprehensive Diffusion Video Forensics (DVF) dataset to advance research in video forgery detection. Extensive experiments demonstrate the superiority of MM-Det++ and highlight the effectiveness of unified multimodal forgery learning in detecting diffusion-generated videos.
Read the full abstract

All authors Xiaohong Liu, Xiufeng Song, Huayu Zheng, Lei Bai, Xiaoming Liu, Guangtao Zhai

Computer Vision

Spotlight: Identifying and Localizing Video Generation Errors Using VLMs

Current text-to-video models (T2V) can generate high-quality, temporally coherent, and visually realistic videos. Nonetheless, errors still often occur, and are more nuanced and local compared to the previous generation of T2V models. While current evaluation paradigms assess video models across diverse dimensions, they typically evaluate videos holistically without identifying when specific errors occur or describing their nature. We address this gap by introducing Spotlight, a novel task aimed at localizing and explaining video-generation errors. We generate 600 videos using 200 diverse textual prompts and three state-of-the-art video generators (Veo 3, Seedance, and LTX-2), and annotate over 1600 fine-grained errors across six types, including motion, physics, and prompt adherence. We observe that adherence and physics errors are predominant and persist across longer segments, whereas appearance-disappearance and body pose errors manifest in shorter segments. We then evaluate current VLMs on Spotlight and find that VLMs lag significantly behind humans in error identification and localization in videos. We propose inference-time strategies to probe the limits of current VLMs on our task, improving performance by nearly 2x. Our task paves a way forward to building fine-grained evaluation tools and more sophisticated reward models for video generators.
Read the full abstract

All authors Aditya Chinchure, Sahithya Ravi, Pushkar Shukla, Vered Shwartz, Leonid Sigal

Computer Vision

Versatile Recompression-Aware Perceptual Image Super-Resolution

Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission. Ignoring recompression is suboptimal as the downstream codec might add additional artifacts to restored images. However, jointly optimizing SR and recompression is challenging, as the codecs are not differentiable and vary in configuration. In this paper, we present Versatile Recompression-Aware Perceptual Super-Resolution (VRPSR), which makes existing perceptual SR aware of versatile compression. First, we formulate compression as conditional text-to-image generation and utilize a pre-trained diffusion model to build a generalizable codec simulator. Next, we propose a set of training techniques tailored for perceptual SR, including optimizing the simulator using perceptual targets and adopting slightly compressed images as the training target. Empirically, our VRPSR achieves 10% - 40% bitrate savings based on Real-ESRGAN and S3Diff under H.264/H.265/H.266 single-picture (intra) compression. Besides, our VRPSR facilitates joint optimization of SR and the post-processing model after recompression.
Read the full abstract

All authors Mingwei He, Tongda Xu, Xingtong Ge, Ming Sun, Chao Zhou, Yan Wang

Computer Vision

Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis

Multimodal survival analysis aims to improve cancer prognosis using heterogeneous biomedical data, such as histopathology images and genomic profiles. A common strategy is to align representations across modalities so that shared signals can be captured. However, strong cross-modal alignment can also remove modality-specific evidence that is critical for survival prediction. In this paper, we revisit multimodal survival learning from a simple observation: effective models should first discover shared patterns across modalities, and then preserve modality-specific signals. This motivates a representation learning principle that we refer to as Together Then Apart. Based on this idea, we propose TTA, a framework that balances cross-modal alignment and representation distinctiveness. TTA first performs prototype-based alignment to capture shared survival-related structures between modalities. It then encourages modality-specific distinctiveness through an anchor-guided contrastive objective. To further account for modality imbalance and noisy correspondences, we model cross-modal interactions using unbalanced optimal transport. We evaluate the proposed approach on multiple TCGA cancer cohorts with paired histopathology and genomic data. TTA consistently improves survival prediction over recent multimodal survival models. Moreover, the learned prototype structures reveal interpretable cross-modal patterns associated with clinical outcomes.
Read the full abstract

All authors Wenjing Liu, Qin Ren, Wen Zhang, Yuewei Lin, Chenyu You

Computer Vision

Less Is More: An Explainable AI Framework for Lightweight Malaria Classification

Background and Objective: Deep learning models have high computational needs and lack interpretability but are often the first choice for medical image classification tasks. This study addresses whether complex neural networks are essential for the simple binary classification task of malaria. We introduce the Extracted Morphological Feature Engineered (EMFE) pipeline, a transparent, reproducible, and low compute machine learning approach tailored explicitly for simple cell morphology, designed to achieve deep learning performance levels on a simple CPU only setup with the practical aim of real world deployment. Methods: The study used the NIH Malaria Cell Images dataset, with two features extracted from each cell image: the number of non background pixels and the number of holes within the cell. Logistic Regression and Random Forest were compared against ResNet18, DenseNet121, MobileNetV2, and EfficientNet across accuracy, model size, and CPU inference time. An ensemble model was created by combining Logistic Regression and Random Forests to achieve higher accuracy while retaining efficiency. Results: The single variable Logistic Regression model achieved a test accuracy of 94.80 percent with a file size of 1.2 kB and negligible inference latency (2.3 ms). The two stage ensemble improved accuracy to 97.15 percent. In contrast, the deep learning methods require 13.6 MB to 44.7 MB of storage and show significantly higher inference times (68 ms). Conclusion: This study shows that a compact feature engineering approach can produce clinically meaningful classification performance while offering gains in transparency, reproducibility, speed, and deployment feasibility. The proposed pipeline demonstrates that simple interpretable features paired with lightweight models can serve as a practical diagnostic solution for environments with limited computational resources.
Read the full abstract

Computer Vision

ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models

Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency. In this work, we present ActDistill, a general action-guided self-derived distillation framework that transfers the action prediction capability of any existing VLA model to a lightweight counterpart. Unlike previous efficiency strategies that primarily emphasize vision-language correlations, ActDistill leverages action priors to guide knowledge transfer and model compression, achieving action-oriented efficiency for VLA models. Specifically, we employ a well-trained VLA model as the teacher and introduce a graph-structured encapsulation strategy to explicitly model the hierarchical evolution of action prediction. The student model, derived from the graph-encapsulated teacher, is further equipped with a dynamic router that adaptively selects computation paths based on action prediction demands, guided by hierarchical graph-informed supervision to ensure smooth and efficient evolution. During inference, graph-related auxiliary components are removed, allowing the student to execute only dynamically routed layers and predict high-precision actions with minimal computation and latency. Experiments on embodied benchmarks demonstrate that ActDistill achieves comparable or superior performance to full-scale VLA models while reducing computation by over 50% with up to 1.67 times speedup, thereby establishing a general paradigm toward efficient embodied intelligence.
Read the full abstract

All authors Wencheng Ye, Tianshi Wang, Lei Zhu, Fengling Li, Guoli Yang, Hengtao Shen

Computer Vision

VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection

To identify objects beyond predefined categories, open-vocabulary aerial object detection (OVAD) leverages the zero-shot capabilities of visual-language models (VLMs) to generalize from base to novel categories. Existing approaches typically utilize self-learning mechanisms with weak text supervision to generate region-level pseudo-labels to align detectors with VLMs semantic spaces. However, text dependence induces semantic bias, restricting open-vocabulary expansion to text-specified concepts. We propose $\textbf{VK-Det}$, a $\textbf{V}$isual $\textbf{K}$nowledge-guided open-vocabulary object $\textbf{Det}$ection framework $\textit{without}$ extra supervision. First, we discover and leverage vision encoder's inherent informative region perception to attain fine-grained localization and adaptive distillation. Second, we introduce a novel prototype-aware pseudo-labeling strategy. It models inter-class decision boundaries through feature clustering and maps detection regions to latent categories via prototype matching. This enhances attention to novel objects while compensating for missing supervision. Extensive experiments show state-of-the-art performance, achieving 30.1 $\mathrm{mAP}^{N}$ on DIOR and 23.3 $\mathrm{mAP}^{N}$ on DOTA, outperforming even extra supervised methods.
Read the full abstract

All authors Jianhang Yao, Yongbin Zheng, Siqi Lu, Wanying Xu, Peng Sun

Computer Vision · Cross-listed from cs.LG

pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data

Test-time adaptation (TTA) in federated learning (FL) is crucial for handling unseen data distributions across clients, particularly when faced with domain shifts and skewed class distributions. Class Imbalance (CI) remains a fundamental challenge in FL, where rare but critical classes are often severely underrepresented in individual client datasets. Although prior work has addressed CI during training through reliable aggregation and local class distribution alignment, these methods typically rely on access to labeled data or coordination among clients, and none address class unsupervised adaptation to dynamic domains or distribution shifts at inference time under federated CI constraints. Revealing the failure of state-of-the-art TTA in federated client adaptation in CI scenario, we propose pFedBBN,a personalized federated test-time adaptation framework that employs balanced batch normalization (BBN) during local client adaptation to mitigate prediction bias by treating all classes equally, while also enabling client collaboration guided by BBN similarity, ensuring that clients with similar balanced representations reinforce each other and that adaptation remains aligned with domain-specific characteristics. pFedBBN supports fully unsupervised local adaptation and introduces a class-aware model aggregation strategy that enables personalized inference without compromising privacy. It addresses both distribution shifts and class imbalance through balanced feature normalization and domain-aware collaboration, without requiring any labeled or raw data from clients. Extensive experiments across diverse baselines show that pFedBBN consistently enhances robustness and minority-class performance over state-of-the-art FL and TTA methods.
Read the full abstract

All authors Md Akil Raihan Iftee, Syed Md. Ahnaf Hasan, Mir Sazzat Hossain, Rakibul Hasan Rajib, Amin Ahsan Ali, AKM Mahbubur Rahman, Sajib Mistry, Monowar Bhuyan

Computer Vision

A Lightweight, Interpretable Deep Learning System for Automated Detection of Cervical Adenocarcinoma In Situ (AIS)

Cervical adenocarcinoma in situ (AIS) is a critical premalignant lesion whose accurate histopathological diagnosis is challenging. Early detection is essential to prevent progression to invasive cervical adenocarcinoma. In this study, we developed a deep learning-based virtual pathology assistant capable of distinguishing AIS from normal cervical gland histology using the CAISHI dataset, which contains 2240 expert-labeled H&E images (1010 normal and 1230 AIS). All images underwent Macenko stain normalization and patch-based preprocessing to enhance morphological feature representation. An EfficientNet-B3 convolutional neural network was trained using class-balanced sampling and focal loss to address dataset imbalance and emphasize difficult examples. The final model achieved an overall accuracy of 0.7323, with an F1-score of 0.75 for the Abnormal class and 0.71 for the Normal class. Grad-CAM heatmaps demonstrated biologically interpretable activation patterns, highlighting nuclear atypia and glandular crowding consistent with AIS morphology. The trained model was deployed in a Gradio-based virtual diagnostic assistant. These findings demonstrate the feasibility of lightweight, interpretable AI systems for cervical gland pathology, with potential applications in screening workflows, education, and low-resource settings.
Read the full abstract

Computer Vision

Hierarchical Semi-Supervised Active Learning for Remote Sensing

The performance of deep learning models in remote sensing (RS) strongly depends on the availability of high-quality labeled data. However, collecting large-scale annotations is costly and time-consuming, while vast amounts of unlabeled imagery remain underutilized. To address this challenge, we propose a Hierarchical Semi-Supervised Active Learning (HSSAL) framework that integrates semi-supervised learning (SSL) and a novel hierarchical active learning (HAL) in a closed iterative loop. In each iteration, SSL refines the model using both labeled data through supervised learning and unlabeled data via weak-to-strong self-training, improving feature representation and uncertainty estimation. Guided by the refined representations and uncertainty cues of unlabeled samples, HAL then conducts sample querying through a progressive clustering strategy, selecting the most informative instances that jointly satisfy the criteria of scalability, diversity, and uncertainty. This hierarchical process ensures both efficiency and representativeness in sample selection. Extensive experiments on three benchmark RS scene classification datasets, including UCM, AID, and NWPU-RESISC45, demonstrate that HSSAL consistently outperforms SSL- or AL-only baselines. Remarkably, with only 8%, 4%, and 2% labeled training data on UCM, AID, and NWPU-RESISC45, respectively, HSSAL achieves over 95% of fully-supervised accuracy, highlighting its superior label efficiency through informativeness exploitation of unlabeled data. Our code will be publicly available.
Read the full abstract

All authors Wei Huang, Zhitong Xiong, Chenying Liu, Xiao Xiang Zhu

Computer Vision

IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment

Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation, text-driven image editing is characterized by simultaneously conditioning on both text and a source image. The edited images often retain an intrinsic connection to the original image, which dynamically change with the semantics of the text. However, previous methods tend to solely focus on text-image alignment or have not well aligned with human perception. In this work, we introduce the Text-driven Image Editing Benchmark suite (IE-Bench) to enhance the assessment of text-driven edited images. IE-Bench includes a database contains diverse source images, various editing prompts and the corresponding edited results from different editing methods, and nearly 4,000 samples with corresponding Mean Opinion Scores (MOS) provided by 15 human subjects. Furthermore, we introduce IE-Critic-R1, which, benefiting from Reinforcement Learning from Verifiable Rewards (RLVR), provides more comprehensive and explainable quality assessment for text-driven image editing that aligns with human perception. Extensive experiments demonstrate IE-Critic-R1's superior subjective-alignments on the text-driven image editing task compared with previous metrics. Related data and codes are available to the public.
Read the full abstract

All authors Bowen Qu, Shangkun Sun, Xiaoyu Liang, Wei Gao

Computer Vision

UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

Diffusion transformers have recently delivered strong text-to-image generation around 1K resolution, but we show that extending them to native 4K across diverse aspect ratios exposes a tightly coupled failure mode spanning positional encoding, VAE compression, and optimization. Tackling any of these factors in isolation leaves substantial quality on the table. We therefore take a data-model co-design view and introduce UltraFlux, a Flux-based DiT trained natively at 4K on MultiAspect-4K-1M, a 1M-image 4K corpus with controlled multi-AR coverage, bilingual captions, and rich VLM/IQA metadata for resolution- and AR-aware sampling. On the model side, UltraFlux couples (i) Resonance 2D RoPE with YaRN for training-window-, frequency-, and AR-aware positional encoding at 4K; (ii) a simple, non-adversarial VAE post-training scheme that improves 4K reconstruction fidelity; (iii) an SNR-Aware Huber Wavelet objective that rebalances gradients across timesteps and frequency bands; and (iv) a Stage-wise Aesthetic Curriculum Learning strategy that concentrates high-aesthetic supervision on high-noise steps governed by the model prior. Together, these components yield a stable, detail-preserving 4K DiT that generalizes across wide, square, and tall ARs. On the Aesthetic-Eval at 4096 benchmark and multi-AR 4K settings, UltraFlux consistently outperforms strong open-source baselines across fidelity, aesthetic, and alignment metrics, and-with a LLM prompt refiner-matches or surpasses the proprietary Seedream 4.0.
Read the full abstract

Computer Vision

Hybrid Event Frame Sensors: Modeling, Calibration, and Simulation

Hybrid event-frame sensors integrate an Event Vision Sensor (EVS) and an Active Pixel Sensor (APS) within a single chip, combining the high dynamic range and low latency of the EVS with the rich spatial intensity information from the APS. While this tight integration offers compact and temporally precise imaging, the complex circuit architecture introduces nontrivial noise patterns that remain poorly understood and unmodeled. In this work, we present the first unified statistics-based imaging noise model that jointly describes the noise behavior of APS and EVS pixels. Our formulation explicitly incorporates photon shot noise, dark current noise, fixed-pattern noise, and quantization noise, and links EVS noise to illumination level and dark current. Based on this formulation, we further develop a calibration pipeline to estimate noise parameters from real data and provide a detailed analysis of both APS and EVS noise behaviors. Finally, we propose H-ESIM, a statistically grounded simulator that generates RAW frames and events under realistic jointly calibrated noise statistics. Experiments on two hybrid sensors validate our model across multiple imaging tasks, including video frame interpolation and deblurring, demonstrating strong transfer from simulation to real data.
Read the full abstract

All authors Yunfan Lu, Nico Messikommer, Xiaogang Xu, Liming Chen, Yuhan Chen, Nikola Zubic, Davide Scaramuzza, Hui Xiong

Computer Vision · Cross-listed from eess.IV

Diverse Instance Generation via Diffusion Models for Enhanced Few-Shot Object Detection in Remote Sensing Images

Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species monitoring and disaster assessment. Existing FSOD methods for remote sensing images (RSIs) have achieved promising progress but remain constrained by the limited diversity of instances. To address this issue, we propose a novel framework that can leverage a diffusion model pretrained on large-scale natural images to synthesize diverse remote sensing instances, thereby improving the performance of few-shot object detectors. Instead of directly synthesizing complete remote sensing images, we first generate instance-level slices via a specialized slice-to-slice module, and then embed these slices into full-scale imagery for enhanced data augmentation. To further adapt diffusion models for remote sensing scenarios, we develop a class-agnostic image inversion module that can invert remote sensing instance slices into semantic space. Additionally, we introduce contrastive loss to semantically align the synthesized images with their corresponding classes. Experimental results show that our method hasachieved an average performance improvement of 4.4% across multiple datasets and various approaches. Ablation experiments indicate that the elaborately designed inversion module can effectively enhance the performance of FSOD methods, and the semantic contrastive loss can further boost the performance.
Read the full abstract

All authors Yanxing Liu, Jiancheng Pan, Jianwei Yang, Tiancheng Chen, Peiling Zhou, Bingchen Zhang

Computer Vision

MambaX: Image Super-Resolution with State Predictive Control

Image super-resolution (SR) is a critical technology for overcoming the inherent hardware limitations of sensors. However, existing approaches mainly focus on directly enhancing the final resolution, often neglecting effective control over error propagation and accumulation during intermediate stages. Recently, Mamba has emerged as a promising approach that can represent the entire reconstruction process as a state sequence with multiple nodes, allowing for intermediate intervention. Nonetheless, its fixed linear mapper is limited by a narrow receptive field and restricted flexibility, which hampers its effectiveness in fine-grained images. To address this, we created a nonlinear state predictive control model MambaX that maps consecutive spectral bands into a latent state space and generalizes the SR task by dynamically learning the nonlinear state parameters of control equations. Compared to existing sequence models, MambaX 1) employs dynamic state predictive control learning to approximate the nonlinear differential coefficients of state-space models; 2) introduces a novel state cross-control paradigm for multimodal SR fusion; and 3) utilizes progressive transitional learning to mitigate heterogeneity caused by domain and modality shifts. Our evaluation demonstrates the superior performance of the dynamic spectrum-state representation model in both single-image SR and multimodal fusion-based SR tasks, highlighting its substantial potential to advance spectrally generalized modeling across arbitrary dimensions and modalities.
Read the full abstract

All authors Chenyu Li, Danfeng Hong, Bing Zhang, Zhaojie Pan, Naoto Yokoya, Jocelyn Chanussot

Computer Vision

Modeling Retinal Ganglion Cells with Neural Differential Equations

This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across three datasets. Compared to a convolutional baseline and an LSTM, both architectures achieved lower MAE, faster convergence, smaller model sizes, and favorable query times, though with slightly lower Pearson correlation. Their efficiency and adaptability make them well suited for scenarios with limited data and frequent retraining, such as edge deployments in vision prosthetics.
Read the full abstract

Computer Vision

State and Scene Enhanced Prototypes for Weakly Supervised Open-Vocabulary Object Detection

Open-Vocabulary Object Detection (OVOD) aims to generalize object recognition to novel categories, while Weakly Supervised OVOD (WS-OVOD) extends this by combining box-level annotations with image-level labels. Despite recent progress, two critical challenges persist in this setting. First, existing semantic prototypes, even when enriched by LLMs, are static and limited, failing to capture the rich intra-class visual variations induced by different object states (e.g., a cat's pose). Second, the standard pseudo-box generation introduces a semantic mismatch between visual region proposals (which contain context) and object-centric text embeddings. To tackle these issues, we introduce two complementary prototype enhancement strategies. To capture intra-class variations in appearance and state, we propose the State-Enhanced Semantic Prototypes (SESP), which generates state-aware textual descriptions (e.g., "a sleeping cat") to capture diverse object appearances, yielding more discriminative prototypes. Building on this, we further introduce Scene-Augmented Pseudo Prototypes (SAPP) to address the semantic mismatch. SAPP incorporates contextual semantics (e.g., "cat lying on sofa") and utilizes a soft alignment mechanism to promote contextually consistent visual-textual representations. By integrating SESP and SAPP, our method effectively enhances both the richness of semantic prototypes and the visual-textual alignment, achieving notable improvements.
Read the full abstract

Computer Vision

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose RoadBench, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using Bird's-Eye View (BEV) and First-Person View (FPV) image inputs. This benchmark comprises eight tasks consisting of 3,040 strictly manually verified test cases, constructed from 2,137 unique BEV images and 721 unique FPV images collected from five Chinese cities with relatively consistent traffic conventions. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 20 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs.
Read the full abstract

All authors Jun Zhang, Xin Zhang, Jie Feng, Long Chen, Junhui Wang, Zhicheng Liu, Depeng Jin, Yong Li

Computer Vision

Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging

Detecting changes in longitudinal medical imaging using deep learning requires a substantial amount of accurately labeled data. However, labeling these images is notably more costly and time-consuming than labeling other image types, as it requires labeling across various time points, where new lesions can be minor, and subtle changes are easily missed. Deep Active Learning (DAL) has shown promise in minimizing labeling costs by selectively querying the most informative samples, but existing studies have primarily focused on static tasks like classification and segmentation. Consequently, the conventional DAL approach cannot be directly applied to change detection tasks, which involve identifying subtle differences across multiple images. In this study, we propose a novel DAL framework, named Longitudinal Medical Imaging Active Learning (LMI-AL), tailored specifically for longitudinal medical imaging. By pairing and differencing all 2D slices from baseline and follow-up 3D images, LMI-AL iteratively selects the most informative pairs for labeling using DAL, training a deep learning model with minimal manual annotation. Experimental results demonstrate that, with less than 8% of the data labeled, LMI-AL can achieve performance comparable to models trained on fully labeled datasets. We also provide a detailed analysis of the method's performance, as guidance for future research. The code is publicly available at https://github.com/HelenMa9998/Longitudinal_AL.
Read the full abstract

All authors Siteng Ma, Honghui Du, Prateek Mathur, Brendan S. Kelly, Ronan P. Killeen, Aonghus Lawlor, Ruihai Dong

Computer Vision

UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale

The automated generation of high-fidelity, city-scale 3D environments remains a formidable challenge with profound academic and industrial implications. However, existing methods struggle to achieve the necessary quality, fidelity, and scalability. To address this, we propose UrbanWorld2.0, a reality-aligned intelligent multimodal synthesis engine that creates detailed, city-scale 3D worlds of high fidelity. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyzes validate the superior performance of UrbanWorld2.0 in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving a win rate of over 86% against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes UrbanWorld2.0 a promising foundation for applications in immersive media, embodied intelligence, and world models.
Read the full abstract

All authors Shengyuan Wang, Zhiheng Zheng, Yu Shang, Lixuan He, Yangcheng Yu, Fan Hangyu, Jie Feng, Qingmin Liao, Yong Li

Computer Vision

SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining

Image deraining is crucial for vision applications but is challenged by the complex multi-scale physics of rain and its coupling with scenes. To address this challenge, a novel approach inspired by multi-stage image restoration is proposed, incorporating Point Spread Function (PSF) mechanisms to reveal the image degradation process while combining dynamic physical modeling with sequential feature fusion transfer, named SD-PSFNet. Specifically, SD-PSFNet employs a sequential restoration architecture with three cascaded stages, allowing multiple dynamic evaluations and refinements of the degradation process estimation. The network utilizes components with learned PSF mechanisms to dynamically simulate rain streak optics, enabling effective rain-background separation while progressively enhancing outputs through novel PSF components at each stage. Additionally, SD-PSFNet incorporates adaptive gated fusion for optimal cross-stage feature integration, enabling sequential refinement from coarse rain removal to fine detail restoration. Our model achieves state-of-the-art PSNR/SSIM metrics on Rain100H (33.12dB/0.9371), RealRain-1k-L (42.28dB/0.9872), and RealRain-1k-H (41.08dB/0.9838). In summary, SD-PSFNet demonstrates excellent capability in complex scenes and dense rainfall conditions, providing a new physics-aware approach to image deraining.
Read the full abstract

All authors Jiayu Wang, Haoyu Bian, Haoran Sun, Shaoning Zeng

Computer Vision

HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation

Accurate organ and lesion segmentation is a critical prerequisite for computer-aided diagnosis. Convolutional Neural Networks (CNNs), constrained by their local receptive fields, often struggle to capture complex global anatomical structures. To tackle this challenge, this paper proposes a novel hybrid architecture, HyM-UNet, designed to synergize the local feature extraction capabilities of CNNs with the efficient global modeling capabilities of Mamba. Specifically, we design a Hierarchical Encoder that utilizes convolutional modules in the shallow stages to preserve high-frequency texture details, while introducing Visual Mamba modules in the deep stages to capture long-range semantic dependencies with linear complexity. To bridge the semantic gap between the encoder and the decoder, we propose a Mamba-Guided Fusion Skip Connection (MGF-Skip). This module leverages deep semantic features as gating signals to dynamically suppress background noise within shallow features, thereby enhancing the perception of ambiguous boundaries. We conduct extensive experiments on public benchmark dataset ISIC 2018. The results demonstrate that HyM-UNet significantly outperforms existing state-of-the-art methods in terms of Dice coefficient and IoU, while maintaining lower parameter counts and inference latency. This validates the effectiveness and robustness of the proposed method in handling medical segmentation tasks characterized by complex shapes and scale variations.
Read the full abstract