Image and Vision Computing最新文献

{"title":"Fidelity-preserving zero-shot diffusion models for highly ill-posed inverse problems in lensless imaging","authors":"Haechang Lee ,&nbsp;Dong Ju Mun ,&nbsp;Hyunwoo Lee ,&nbsp;Kyung Chul Lee ,&nbsp;Seongmin Hong ,&nbsp;Gwanghyun Kim ,&nbsp;Seung Ah Lee ,&nbsp;Se Young Chun","doi":"10.1016/j.imavis.2025.105786","DOIUrl":"10.1016/j.imavis.2025.105786","url":null,"abstract":"<div><div>Diffusion models have been extensively explored for solving ill-posed inverse problems, achieving remarkable performance. However, their applicability to real-world scenarios, such as lensless imaging, has not been well investigated. Modern lensless imaging has compact form factor, low-cost hardware requirement, and intrinsic compressive imaging capabilities, but these advantages pose highly ill-posed inverse problems. In this work, we introduce a training-free zero-shot diffusion model, termed <strong>Dilack</strong>, for restoring raw images captured by lensless cameras that are degraded by large and complex kernels. Our approach incorporates novel data fidelity terms, referred to as the pseudo-inverse anchor for constraining (PiAC) fidelity loss, to enhance reconstruction quality by addressing the ill-posed nature of challenging inverse problems. Additionally, inspired by locally acting classical regularizers, we propose integrating masked fidelity within the PiAC loss. This scheme enables interaction with globally acting diffusion models while adaptively enforcing spatially and stepwise local fidelity through masks. Our proposed framework effectively mitigates erratic behavior and inherent artifacts in diffusion models when used for highly ill-posed inverse problems, significantly improving the quality of lensless camera raw image restoration, including perceptual aspects. Experimental results on both synthetic and real-world datasets for modern lensless imaging demonstrate that our approach outperforms prior arts including classical and existing diffusion based methods. The code is available at <span><span>https://github.com/mundongju/Dilack</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105786"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145521237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large-small model collaboration for medical visual question answering with task aware mixture of experts and relation knowledge distillation","authors":"Qishen Chen ,&nbsp;Wenxuan He ,&nbsp;Xingyuan Chen ,&nbsp;Chen Cheng ,&nbsp;Minjie Bian ,&nbsp;Huahu Xu","doi":"10.1016/j.imavis.2025.105820","DOIUrl":"10.1016/j.imavis.2025.105820","url":null,"abstract":"<div><div>Medical visual question answering aims to support clinical decision-making by answering natural language questions about medical images. In this domain, specialized task-specific small models often surpass large medical vision–language models due to stronger task alignment and domain-specific expertise. However, these small models lack broad domain knowledge necessary for high-level diagnostic reasoning, such as identifying disease causes or recommending treatments. To address these limitations, this paper presents CoMed-TR, a collaborative framework that integrates multiple large medical vision–language models with a task–specific small model to achieve robust and accurate medical visual question answering. The framework introduces a domain-specific vision–language embedding model, Med-Vec, trained on large-scale medical data to produce rich joint image–text representations. A Task-Aware Mixture-of-Experts module dynamically selects and weights heterogeneous experts, including pretrained medical vision–language models and a segmentation-based image encoder-based on question semantics, enabling adaptive expert fusion. In addition, a relation knowledge distillation strategy aligns the fused expert representations with the relational structure learned by Med-Vec, embedding clinically meaningful similarity relationships into the model’s representation space. Experiments on two public benchmarks demonstrate that CoMed-TR achieves significant performance gains, improving overall accuracy by 3.3% on the VQA-RAD dataset and 1.1% on SLAKE, outperforming both prior state-of-the-art models and existing large–small collaboration methods. Notably, these results are achieved with only approximately 25 million trainable parameters, highlighting the framework’s computational efficiency and practical potential for deployment in real-world clinical settings. The codes are available at: <span><span>https://github.com/shanziSZ/CoMed-TR/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105820"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Better early detector for high-performance detection transformer","authors":"Bin Hu ,&nbsp;Bencheng Liao ,&nbsp;Jiyang Qi ,&nbsp;Shusheng Yang ,&nbsp;Wenyu Liu","doi":"10.1016/j.imavis.2025.105829","DOIUrl":"10.1016/j.imavis.2025.105829","url":null,"abstract":"<div><div>Transformers are revolutionizing the landscape of artificial intelligence, unifying the architecture for natural language processing, computer vision, and more. In this paper, we explore how far a Transformer-based architecture can go for object detection - a fundamental task in computer vision and applicable across a range of engineering applications. We found that introducing an early detector can improve the performance of detection transformers, allowing them to know where to focus. To this end, we propose a novel attention map to feature map auxiliary loss and a novel local bipartite matching strategy to cost-freely get a BEtter early detector for high-performance detection TRansformer (BETR). On the COCO dataset, BETR adds no more than 6 million parameters to the Swin Transformer backbone, achieving the highest AP and latency among existing fully Transformer-based detectors across different model scales. As a Transformer detector, BETR also demonstrates accuracy, speed, and parameters on par with previous state-of-the-art CNN-based GFLV2 framework for the first time.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105829"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CFE-PVTSeg:Cross-domain frequency-enhanced pyramid vision transformer segmentation network","authors":"Niu Guo,&nbsp;Yi Liu,&nbsp;Pengcheng Zhang,&nbsp;Jiaqi Kang,&nbsp;Zhiguo Gui,&nbsp;Lei Wang","doi":"10.1016/j.imavis.2025.105824","DOIUrl":"10.1016/j.imavis.2025.105824","url":null,"abstract":"<div><div>Current polyp segmentation methods predominantly rely on either standalone Convolutional Neural Networks (CNNs) or Transformer architectures, which exhibit inherent limitations in balancing global–local contextual relationships and preserving high-frequency structural details. To address these challenges, this study proposes a Cross-domain Frequency-enhanced Pyramid Vision Transformer Segmentation Network (CFE-PVTSeg). In the encoder, the network achieves hierarchical feature enhancement by integrating Transformer encoders with wavelet transforms: it separately extracts multi-scale spatial features (based on Pyramid Vision Transformer) and frequency-domain features (based on Discrete Wavelet Transform), reinforcing high-frequency components through a cross-domain fusion mechanism. Simultaneously, deformable convolutions with enhanced adaptability are combined with regular convolutions for stability to aggregate boundary-sensitive features that accommodate the irregular morphological variations of polyps. In the decoder, an innovative Multi-Scale Feature Uncertainty Enhancement (MS-FUE) module is designed, which leverages an uncertainty map derived from the encoder to adaptively weight and refine upsampled features, thereby effectively suppressing uncertain components while enhancing the propagation of reliable information. Finally, through a multi-level fusion strategy, the model outputs refined features that deeply integrate high-level semantics with low-level spatial details. Extensive experiments on five public benchmark datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS, and CVC-300) demonstrate that CFE-PVTSeg achieves superior robustness and segmentation accuracy compared to existing methods when handling challenging scenarios such as scale variations and blurred boundaries. Ablation studies further validate the effectiveness of both the proposed cross-domain enhanced encoder and the uncertainty-driven decoder, particularly in suppressing feature noise and improving morphological adaptability to polyps with heterogeneous appearance characteristics.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105824"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CMDiff: Clip-guided multi-dimension mamba diffusion model for low light image enhancement","authors":"Chengbo Yu ,&nbsp;Dengshi Li ,&nbsp;Jia Wei ,&nbsp;Yulin Wu ,&nbsp;AoLei Chen","doi":"10.1016/j.imavis.2025.105787","DOIUrl":"10.1016/j.imavis.2025.105787","url":null,"abstract":"<div><div>Significant progress has been made in low-light image enhancement techniques, but unstable image quality recovery and suboptimal visual perception remain challenges. To address these issues, we propose a robust low-light image enhancement method, CLIP-guided multi-dimension mamba diffusion (CMDiff). Our framework utilizes the CLIP model for scene information guidance via feature modulation to enhance the model’s perception of scene details. We combine the multidimension Mamba block with UNet to construct a denoising network that leverages Mamba’s strengths in processing long sequences and global contextual information. The multi-dimension Mamba module integrates key information from multiple image dimensions with linear time complexity, thus facilitating effective and comprehensive feature learning. Extensive experiments on real-world benchmarks show that our approach outperforms state-of-the-art methods in terms of image quality and noise rejection.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105787"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145468938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EmbryoVision AI: An explainable deep learning framework for enhanced blastocyst selection in assisted reproductive technologies","authors":"Alessia Auriemma Citarella ,&nbsp;Pietro Battistoni ,&nbsp;Chiara Coscarelli ,&nbsp;Fabiola De Marco ,&nbsp;Luigi Di Biasi ,&nbsp;Mengyuan Wang","doi":"10.1016/j.imavis.2025.105795","DOIUrl":"10.1016/j.imavis.2025.105795","url":null,"abstract":"<div><div>Accurate embryo selection is a key factor in improving implantation success rates in Assisted Reproductive Technologies. This study presents a deep learning framework, <em>EmbryoVision AI</em>, designed to enhance blastocyst assessment using Time-Lapse Imaging and eXplainable AI techniques. A customized convolutional neural network was developed to capture both morphological and temporal dynamics, enabling a precise classification of the embryo. To ensure transparency, Gradient-weighted Class Activation Mapping was integrated, allowing visualization of decision-critical embryonic structures and ensuring clinical alignment. The model demonstrated strong predictive performance across different embryo grades, achieving an accuracy of 91.5% for Grade AA, 88.4% for Grade AB, and 79.3% for Grade BC. The AUC-ROC values were 0.95, 0.90, and 0.81 for Grade AA, AB, and BC, respectively, indicating strong discriminatory capabilities. The findings suggest that AI-driven embryo selection can enhance objectivity, reduce human variability, and improve ART outcomes. However, the results also underscore the need to refine AI models to better handle morphological variability in lower-quality embryos, highlighting the importance of improving generalization and strengthening clinical integration.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105795"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145468942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CAGS: Open-vocabulary 3D scene understanding with context-aware Gaussian splatting","authors":"Wei Sun ,&nbsp;Yuan Li ,&nbsp;Jianbin Jiao","doi":"10.1016/j.imavis.2025.105830","DOIUrl":"10.1016/j.imavis.2025.105830","url":null,"abstract":"<div><div>Open-vocabulary 3D scene understanding is crucial for applications requiring natural language-driven spatial interpretation, such as robotics and augmented reality. While 3D Gaussian Splatting (3DGS) offers a powerful representation for scene reconstruction, integrating it with open-vocabulary frameworks reveals a key challenge: <em>cross-view granularity inconsistency</em>. This issue, stemming from 2D segmentation methods like the Segment Anything Model (SAM), results in inconsistent object segmentations across views (e.g., a ”coffee set” segmented as a single entity in one view but as ”cup + coffee + spoon” in another). Existing 3DGS-based methods often rely on isolated per-Gaussian feature learning, neglecting the spatial context needed for cohesive object reasoning, leading to fragmented representations. We propose <em>Context-Aware Gaussian Splatting (CAGS)</em>, a novel framework that addresses this challenge by incorporating spatial context into 3DGS. CAGS constructs local graphs to propagate contextual features across Gaussians, reducing noise from inconsistent granularity, employs mask-centric contrastive learning to smooth SAM-derived features across views, and leverages a precomputation strategy to reduce computational cost by precomputing neighborhood relationships, enabling efficient training in large-scale scenes. By integrating spatial context, CAGS significantly improves 3D instance segmentation and reduces fragmentation errors on datasets like LERF-OVS and ScanNet, enabling robust language-guided 3D scene understanding.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105830"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semi-supervised medical image segmentation via anatomy-preserving consistency training","authors":"Shiman Li ,&nbsp;Siqi Yin ,&nbsp;Haoran Wang ,&nbsp;Chenxi Zhang ,&nbsp;Zhijian Song","doi":"10.1016/j.imavis.2025.105833","DOIUrl":"10.1016/j.imavis.2025.105833","url":null,"abstract":"<div><div>Due to the scarcity of large numbers of dense annotations in the medical field, semi-supervised learning (SSL) is a popular way for medical image segmentation, leveraging limited labeled data and large amounts of unlabeled data. Consistency regularization is a promising technique of SSL approaches, which exploits unlabeled data by encouraging consistency under perturbations. However, existing perturbations often confuse or destroy anatomical contextual information, resulting in fragmented and false positive prediction results. To address this issue, an anatomy-preserving consistency training method is proposed for semi-supervised medical image segmentation. Specifically, Non-Linear Transformation (NLT) is employed on input images to generate weak and strong augmentation, helping the network learn about anatomical appearance (shape and intensity distribution) without distorting anatomical structure. Apart from regularization at the output level, an Attention-guided Multi-scale Feature Consistency (AMFC) is imposed on the feature level to learn transformation-invariant robust anatomical representations and reduce prediction noise. Experimental results show that our method achieves state-of-the-art performance on three public datasets, ACDC, BraST2019, and PDDCA, with high label efficiency, showing the generality and promising potential of our method for medical care.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105833"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145624271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PACMAN: Rapid identification of keypoint patch-based fiducial marker in occluded environments","authors":"Taewook Park ,&nbsp;Geunsik Bae ,&nbsp;Woojae Shin ,&nbsp;Meraj Mammadov ,&nbsp;Jaemin Seo ,&nbsp;Heejung Shin ,&nbsp;Hyondong Oh","doi":"10.1016/j.imavis.2025.105821","DOIUrl":"10.1016/j.imavis.2025.105821","url":null,"abstract":"<div><div>Fiducial marker systems are widely used in image-based localization methods due to their high robustness and low computational latency. However, occlusions caused by dynamic environmental factors, such as shadows and unexpected objects, significantly hinder the detection of fiducial markers, as partially visible patterns and significant image degradation often contradict the fundamental assumptions of marker detection systems. To address this challenge, we propose a keypoint-based fiducial marker and a deep-learning-based detector that jointly handle occlusion and image degradation with minimal computational latency. First, we design four distinct keypoint patches that account for occlusions and maintain essential functionalities. A fiducial marker is then constructed by assembling six identical patches under geometric constraints. Second, a widely-used interest point detector network is optimized for the proposed marker design, resulting in robust keypoint detection under various types of image deformation and degradation. A geometric consistency check is subsequently applied to map imperfect keypoint detections to 6D marker poses in the image, effectively rejecting occlusions and potential network failures. Third, neural network quantization and parallel CPU processing are applied to minimize computational latency. Our experimental results demonstrate higher detection rates then other types of single marker in occluded environments, with improvements ranging from 17% to 40%. The proposed system is also evaluated under motion blur, dimming effects, and variations in scale and rotation. Additionally, the efficient computational design enables end-to-end processing at up to 749 FPS on a desktop PC and 138 FPS on an edge device, for 640 × 480 resolution images containing a single marker. Our code is available at: <span><span>https://github.com/WhiteCri/PACMAN.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105821"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ABENet: Attention-based bidirectional enhancement network for collaborative camouflaged object detection","authors":"Cong Zhang ,&nbsp;Shiyuan Li ,&nbsp;Yulin Zeng,&nbsp;Yuhui Gao,&nbsp;Hongbo Bi","doi":"10.1016/j.imavis.2025.105817","DOIUrl":"10.1016/j.imavis.2025.105817","url":null,"abstract":"<div><div>Camouflaged object detection (COD) aims to identify targets that are highly similar in appearance or color to their background, presenting an extremely challenging task. Existing methods primarily focus on single object detection, neglecting the potential for collaborative camouflaged behavior between targets, resulting in inadequate performance in scenarios with multiple target interferences and complex backgrounds. To address this, we propose a novel collaborative camouflaged object detection (CoCOD) framework—Attention-based Bidirectional Enhancement Network (ABENet). Specifically, we design two core modules: the Shifted Cooperative Attention Module (SCAM) and the Gated Bidirectional Enhancement Module (GBEM). The SCAM introduces a shifted window attention mechanism to facilitate efficient feature interaction between local and global contexts, combined with multi-scale receptive fields and channel selectors to enhance the response capability to critical camouflaged regions, and the GBEM employs a gated mechanism to achieve bidirectional enhancement between high- and low-level features, integrating contextual semantic information to enhance the effectiveness and robustness of collaborative camouflaged object detection tasks. Extensive experiments on the CoCOD8K dataset demonstrate that our proposed ABENet outperforms 10 state-of-the-art COD methods, 7 co-salient object detection (CoSOD) models, and 7 CoCOD approaches, as evaluated by six widely used metrics.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"165 ","pages":"Article 105817"},"PeriodicalIF":4.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145468940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}