{"generated_at":"2026-10-10T02:21:18Z","total":452,"page":0,"pages":5,"page_size":100,"next":"/api/catalog?topic=image-video-processing&page=1","documents":[{"id":"arxiv-2505.14717","title":"AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD","year":2026,"authors":["Xigui Li","Yuanye Zhou","Feiyang Xiao"],"author_count":19,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI","cs.CV","cs.LG"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2505.14717","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-07efb23eda3c5defa468","title":"AXIAL: Attention-based eXplainability for Interpretable Alzheimer's Localized Diagnosis using 2D CNNs on 3D MRI brain scans","year":2024,"authors":["Gabriele Lozupone","Alessandro Bria","Francesco Fontanella"],"author_count":5,"journal":"BMC Medical Informatics and Decision Making (2026)","doi":"10.1186/s12911-026-03833-2","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-07efb23eda3c5defa468","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2602.22691","title":"U-Net-Based Generative Joint Source-Channel Coding for Wireless Image Transmission","year":2026,"authors":["Ming Ye","Kui Cai","Cunhua Pan"],"author_count":7,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2602.22691","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2606.04376","title":"SAGE-Flow: A Decoupled Framework for Geometry Alignment and Stateless Real-Time Multi-Camera 3D Reconstruction","year":2026,"authors":["Chentian Sun"],"author_count":1,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.MM"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2606.04376","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.38264","title":"Disentangling and Fusing Neurostructural and Vascular Ageing for Retinal Age Prediction","year":2026,"authors":["Junwen Zheng","Li Rong Wang","Anthony Zihan Lin"],"author_count":8,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.38264","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.38265","title":"Raw Imagery Impacting Your AI: Should You Care?","year":2026,"authors":["Adrien Dorise","Marjorie Bellizzi","Stéphane May"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.38265","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-85a65eb659f0287a08d1","title":"Colorectal Cancer Segmentation with Adaptive Augmentation and Multi-Resolution Ensemble Models","year":2026,"authors":["Ümit Mert Çağlar","Alptekin Temizel"],"author_count":2,"journal":"Proc. SPIE 14114, Eighteenth International Conference on Machine Vision (ICMV 2025), 141140I (25 Feb 2026)","doi":"10.1117/12.3096537","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/doi-85a65eb659f0287a08d1","fulltext_endpoint":"/api/document/doi-85a65eb659f0287a08d1/fulltext","references_endpoint":null},{"id":"arxiv-2609.38635","title":"TSGL: Teacher-Student Graph Learning for 3DGS Compression","year":2026,"authors":["Matin Bani Saedi","Matthew Kyan","Gene Cheung"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.38635","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.38644","title":"Joint Supervised and Self-Supervised Training with Acquisition-Robust Techniques for Accelerated 4D Flow MRI Reconstruction","year":2026,"authors":["Mengyuan Xue","Bochun Mei"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2609.38644","fulltext_endpoint":"/api/document/arxiv-2609.38644/fulltext","references_endpoint":null},{"id":"arxiv-2609.38680","title":"ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images","year":2026,"authors":["Shubhang Bhatnagar","Ishan Bhatnagar","Viraj Shah"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.AI","cs.LG","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.38680","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.39202","title":"3D Reconstruction from Arthroscopic Images using NeRF: a preliminary in-silico study","year":2026,"authors":["Hermine Kitio Tsamo","Agathe Yvinou","Daniel Pizarro"],"author_count":9,"journal":"International Society for Computer Assisted Orthopaedic Surgery (CAOS), Jun 2026, Matusyama, Japan","doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.39202","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-2a616e4423f8da6e5e93","title":"Deep Learning for Restoring MPI System Matrices Using Simulated Training Data","year":2026,"authors":["Artyom Tsanda","Sarah Reiss","Konrad Scheffler"],"author_count":5,"journal":"Physics in Medicine & Biology (2026)","doi":"10.1088/1361-6560/ae6016","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-2a616e4423f8da6e5e93","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2602.08538","title":"Trajectory Stitching for Solving Inverse Problems with Flow-Based Models","year":2026,"authors":["Alexander Denker","Zeljko Kereta","Carola-Bibiane Schönlieb"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.LG"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2602.08538","fulltext_endpoint":"/api/document/arxiv-2602.08538/fulltext","references_endpoint":null},{"id":"arxiv-2607.24441","title":"Rapid quantitative chemical composition mapping using model-based MRI reconstruction with field inhomogeneity correction","year":2026,"authors":["Artyom Tsanda","Stefan Benders","Muhammad Adrian"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","q-bio.QM"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2607.24441","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.00188","title":"Uncertainty-Aware RL-Controlled Adaptive 3D Mapping","year":2026,"authors":["Alpay Ozkan","Tunc Ozan Aydin","Marc Pollefeys"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.LG","cs.CV","cs.GR","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.00188","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-e80636794112eaaccbb9","title":"ShatterQuant: Breaking Uniform Precision with Block-Wise Mixed-Precision on a Systolic Transformer Hardware Accelerator","year":2026,"authors":["Mikolaj Walczak","Edward Humes","Chao Fang"],"author_count":5,"journal":null,"doi":"10.1145/3831252.3845843","source":"arxiv","topics":["image-video-processing"],"keywords":["cs.AR","cs.AI","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/doi-e80636794112eaaccbb9","fulltext_endpoint":"/api/document/doi-e80636794112eaaccbb9/fulltext","references_endpoint":null},{"id":"arxiv-2610.00319","title":"EgoRefine: Ego-Referenced Predictive Alignment and Trajectory-Conditioned Reliability-Aware Fusion for Asynchronous Collaborative Perception","year":2026,"authors":["Lingzhao Kong","Yongsheng Zang","Yu Kang"],"author_count":7,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.RO","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.00319","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.00384","title":"RIQE: a NIQE-style reference model for Computed Tomography","year":2026,"authors":["Fabio Mattiussi"],"author_count":1,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.00384","fulltext_endpoint":"/api/document/arxiv-2610.00384/fulltext","references_endpoint":null},{"id":"arxiv-2610.00553","title":"Hetero-modal learning and corruption-resistant hetero-modal inference for joint segmentation of white matter hyperintensities and ischaemic stroke lesions in MRI","year":2026,"authors":["Jesse Phitidis","William N. Whiteley","Joanna M. Wardlaw"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.00553","fulltext_endpoint":"/api/document/arxiv-2610.00553/fulltext","references_endpoint":null},{"id":"arxiv-2610.00602","title":"CPathOGen: Spatially and Morphologically Controlled H&E Counterfactuals for Probing Pathology Models","year":2026,"authors":["Samarth Singhal","Varang Rai"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","q-bio.QM"],"license":"CC-BY-4.0","has_fulltext":false,"has_references":false,"rights_class":"licensed_content","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.00602","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.00743","title":"Synthetic-to-Real Transfer in Cerebral Microbleed Generation and Segmentation","year":2026,"authors":["To-Liang Hsu","Ting-Yu Lai","Ching-Ting Lin"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.00743","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.00805","title":"Spatially Gated Diffusion for Localized Counterfactual Chest Radiograph Editing","year":2026,"authors":["Kamran Ullah Afaq","Basit Raza"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.00805","fulltext_endpoint":"/api/document/arxiv-2610.00805/fulltext","references_endpoint":null},{"id":"arxiv-2610.00860","title":"MorphoBranch: A Fine-Structure-Preserving Workbench for Morphometric Analysis of Branched Cellular Structures","year":2026,"authors":["Song Zhiying","Ling Hanyi","Wu Junyi"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","q-bio.QM"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.00860","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.00878","title":"UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking","year":2026,"authors":["Pengfei Qi","Haoran Lin","Sizhuang Chen"],"author_count":10,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.RO","cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.00878","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.01056","title":"HierGF: Hierarchical Gaussian Fields via Geometry-perception Message Passing for Sparse-view 3D Reconstruction","year":2026,"authors":["Bi'an Du","Zhimin Zhang","Daizong Liu"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.01056","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.01060","title":"RC-aware nnU-Netv2 for Pre-treatment and Post-treatment Glioma Segmentation Using Multimodal MRI","year":2026,"authors":["Lin Qu","Ziqi Chen","Anqi Wu"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.01060","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.01655","title":"MDIRNET: Multi-Degradation Image Restoration Network via Deep Unfolding","year":2026,"authors":["Talha Nadeem","Arslan Majal","Muhammad Tahir"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.01655","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.01894","title":"A foundation for systematic analysis of transformers and RNNs for tractography","year":2026,"authors":["Emmanuelle Renauld","Philippe Poulin","Hugo Larochelle"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.LG","eess.IV","q-bio.NC"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.01894","fulltext_endpoint":"/api/document/arxiv-2610.01894/fulltext","references_endpoint":null},{"id":"arxiv-2610.02112","title":"Binary Phase Retrieval of Cosine Transforms via Local Curvature Minimization","year":2026,"authors":["Ronald Ogden","Shwetadwip Chowdhury","Takashi Tanaka"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.02112","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.02136","title":"MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI","year":2026,"authors":["Negin Kafee Hernashki","Soumick Chatterjee"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.AI","eess.IV","physics.med-ph"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.02136","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.39624","title":"ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction","year":2026,"authors":["Mehmet Emre Andıran","Zhuoqian Yang","Liying Lu"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.39624","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-d9f83c681a422e94e294","title":"PlantPlotGAN: A Physics-Informed Generative Adversarial Network for Plant Disease Prediction","year":2023,"authors":["Felipe A. Lopes","Vasit Sagan","Flavio Esposito"],"author_count":3,"journal":null,"doi":"10.1109/wacv57701.2024.00691","source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.LG","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-d9f83c681a422e94e294","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.32824","title":"Unlocking Geodesic Gromov-Wasserstein Distances for 3D Modeling","year":2026,"authors":["Krzysztof Marcin Choromanski","Derek Long","Ananya Parashar"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["algorithms-complexity","image-video-processing"],"keywords":["cs.CV","cs.DS","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2609.32824","fulltext_endpoint":"/api/document/arxiv-2609.32824/fulltext","references_endpoint":null},{"id":"arxiv-2610.02263","title":"ZAGNet: Zone-Aware Graph Aggregation Network for Patient-Level Lung Ultrasound Diagnosis","year":2026,"authors":["Li Chen","Shubham Patil","Rashid Al Mukaddim"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.02263","fulltext_endpoint":"/api/document/arxiv-2610.02263/fulltext","references_endpoint":null},{"id":"arxiv-2610.02265","title":"Event-guided Neural Video Compression","year":2026,"authors":["Jiyun Kong","Jungwoo Kim","Enes Eray Demirtas"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","cs.MM"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.02265","fulltext_endpoint":"/api/document/arxiv-2610.02265/fulltext","references_endpoint":null},{"id":"doi-4c01050c84727b010c47","title":"Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging","year":2026,"authors":["Xinye Yang","Zhusi Zhong","Scott Collins"],"author_count":10,"journal":"Smart Health 41 (2026) 100689","doi":"10.1016/j.smhl.2026.100689","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","cs.LG"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/doi-4c01050c84727b010c47","fulltext_endpoint":"/api/document/doi-4c01050c84727b010c47/fulltext","references_endpoint":null},{"id":"doi-89c2d7f66d3ce6005880","title":"Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models","year":2026,"authors":["Xinye Yang","Zhusi Zhong","Scott Collins"],"author_count":6,"journal":"2026 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pp. 428-433","doi":"10.1109/chase69719.2026.00073","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-89c2d7f66d3ce6005880","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.02675","title":"One Photon, Many Worlds: Posteriors and Predictions with Single-Photon Cameras","year":2026,"authors":["Haejoon Lee","Mohit Gupta","Vijayakumar Bhagavatula"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.02675","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.02799","title":"FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters","year":2026,"authors":["Wenya Su","Kai Luo","Di Wen"],"author_count":8,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.RO","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.02799","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-9eabc946124504b12d2c","title":"Optimizing Breast Cancer Detection in Mammograms: A Comprehensive Study of Transfer Learning, Resolution Reduction, and Multi-View Classification","year":2026,"authors":["Daniel G. P. Petrini","Hae Yong Kim"],"author_count":2,"journal":null,"doi":"10.1002/ima.70436","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/doi-9eabc946124504b12d2c","fulltext_endpoint":"/api/document/doi-9eabc946124504b12d2c/fulltext","references_endpoint":null},{"id":"arxiv-2503.09368","title":"PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens","year":2026,"authors":["Nikolai Körber","Eduard Kromer","Andreas Siebert"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2503.09368","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2409.14204","title":"A Unified Deep Learning Framework for Motion Correction in Medical Imaging","year":2026,"authors":["Jian Wang","Razieh Faghihpirayesh","Danny Joca"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2409.14204","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2505.02256","title":"OASIS: Optimized Lightweight Autoencoder System for Distributed In-Sensor computing","year":2026,"authors":["Chengwei Zhou","Sreetama Sarkar","Yuming Li"],"author_count":8,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2505.02256","fulltext_endpoint":"/api/document/arxiv-2505.02256/fulltext","references_endpoint":null},{"id":"arxiv-2510.26834","title":"MedForj: An open, large-scale foundational generative prior for high-resolution 3D brain MRI","year":2026,"authors":["Samuel W. Remedios","Aaron Carass","Jerry L. Prince"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI"],"license":"CC-BY-SA-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2510.26834","fulltext_endpoint":"/api/document/arxiv-2510.26834/fulltext","references_endpoint":null},{"id":"arxiv-2510.16444","title":"RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Multi-Trajectory Semantic Retrieval","year":2026,"authors":["Kunyu Peng","Di Wen","Jia Fu"],"author_count":12,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.MM","cs.RO","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2510.16444","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2603.09737","title":"$M^2$-Occ: Resilient 3D Semantic Occupancy Prediction for Autonomous Driving with Incomplete Camera Inputs","year":2026,"authors":["Kaixin Lin","Kunyu Peng","Di Wen"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.RO","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2603.09737","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-86cea6f1d11618523a2d","title":"Underwater imaging without color distortions requires RAW capture","year":2026,"authors":["Derya Akkaynak","Michael S. Brown"],"author_count":2,"journal":"Methods in Ecology and Evolution (2026)","doi":"10.1111/2041-210x.70417","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/doi-86cea6f1d11618523a2d","fulltext_endpoint":"/api/document/doi-86cea6f1d11618523a2d/fulltext","references_endpoint":null},{"id":"doi-5a2d54871d4c96336260","title":"Adaptive Fused Prior Transfer for Controllable Generative Image Compression","year":2026,"authors":["Yifei Pei","Ying Liu","Nam Ling"],"author_count":3,"journal":"IEEE Access (2026)","doi":"10.1109/access.2026.3737467","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-5a2d54871d4c96336260","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2605.23508","title":"DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches","year":2026,"authors":["Chuanzhi Xu","Huiqi Liang","Bang Shi"],"author_count":10,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.GR","cs.AI","cs.CV","cs.MM","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2605.23508","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2608.29167","title":"Feature-Spectral Fragility in Segmentation: Dataset Dependence, Architecture-Specific Localization, and Spectral Correlates","year":2026,"authors":["Subhash Kashyap"],"author_count":1,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2608.29167","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.40083","title":"The Effect of Tissue Detection on False Positives of Diffusion-Based Artifact Detection in Histopathology","year":2026,"authors":["Konstantinos Moutselos","Ilias Maglogiannis"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.40083","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.03733","title":"Rare Disease Classification in Video Capsule Endoscopy","year":2026,"authors":["Amit Kumar Patel","Debesh Jha"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["q-bio.TO","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.03733","fulltext_endpoint":"/api/document/arxiv-2610.03733/fulltext","references_endpoint":null},{"id":"arxiv-2610.03739","title":"Deep Learning Denoising of Real SWOT Sea Surface Height Observations","year":2026,"authors":["Gaétan Meis","Anaëlle Tréboutte","Maxime Ballarotta"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["physics.ao-ph","cs.LG","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.03739","fulltext_endpoint":"/api/document/arxiv-2610.03739/fulltext","references_endpoint":null},{"id":"arxiv-2610.03817","title":"Image-Based Breast Implant Detection for Mammography Dataset Curation and Near-Real-Time Deployment: Comparing Foundation Models and Task-Specific Convolutional Models","year":2026,"authors":["Vasisht Ishwar","Hari Trivedi","Young Seok Jeon"],"author_count":8,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","q-bio.TO"],"license":"CC0-1.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.03817","fulltext_endpoint":"/api/document/arxiv-2610.03817/fulltext","references_endpoint":null},{"id":"arxiv-2610.04258","title":"FloVMos: Optical Flow-based Medical Video Mosaicking","year":2026,"authors":["Jinyang Liu","Sandesh Ghimire","Chaman Singh"],"author_count":8,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.04258","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.05426","title":"Distortion-Free High-Resolution PROPELLER-DWI: Technical Advances and Initial Demonstration for the Prostate","year":2026,"authors":["Jingjia Chen","Kun Zhou","Haoyang Pei"],"author_count":10,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.05426","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.05182","title":"TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution","year":2026,"authors":["Chun-An Lin","Tsung-Jung Liu","Yen-Chieh Ouyang"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","cs.LG"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.05182","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.06034","title":"How well do routinely collected demographic and clinical variables aid point-of-care lung ultrasound TB classification","year":2026,"authors":["Joshua M. Jansen van Vüren","Christiaan M. Geldenhuys","Devendra S. Parihar"],"author_count":10,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","cs.LG"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.06034","fulltext_endpoint":"/api/document/arxiv-2610.06034/fulltext","references_endpoint":null},{"id":"arxiv-2610.06051","title":"AI-Driven XR Situational Awareness Platform for Urban Crisis Management and Smart Mobility Operations","year":2026,"authors":["Dimitris Spyridonidis","Gerasimos Arvanitis","Konstantinos Moustakas"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.06051","fulltext_endpoint":"/api/document/arxiv-2610.06051/fulltext","references_endpoint":null},{"id":"arxiv-2610.06579","title":"Right Bregman proximal gradient with application to Poisson inverse problems *","year":2026,"authors":["Thibaut Modrzyk","Elie Bretin","Voichita Maxim"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","math.OC"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.06579","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.06107","title":"Diffusion Meets Unrolling: Compressive SAR Image Reconstruction with Interleaved Learned Corrections","year":2026,"authors":["Odysseas Pappas","Andrew C. M. Austin","Perla Mayo"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.06107","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.06596","title":"Analysis of SWIR Imaging Detection Performance Under Adverse Environmental Conditions for Autonomous Driving Systems","year":2026,"authors":["Rohan Mehra","Alexandre Riffard","Yannis Loumouamou"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.06596","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-dc8b55ba06bee46558ee","title":"Resolving quantitative MRI model degeneracy in self-supervised machine learning","year":2026,"authors":["Giulio V. Minore","Louis Dwyer-Hemmings","Timothy J. P. Bray"],"author_count":4,"journal":"Information Processing in Medical Imaging. IPMI 2025. Lecture Notes in Computer Science, vol 15830. Springer, Cham","doi":"10.1007/978-3-031-96625-5_13","source":"arxiv","topics":["image-video-processing"],"keywords":["physics.med-ph","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-dc8b55ba06bee46558ee","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2501.01908","title":"Training-Free Adversarial Robustness in Computational MRI","year":2026,"authors":["Mahdi Saberi","Chi Zhang","Mehmet Akçakaya"],"author_count":3,"journal":"Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:106681-106710, 2026","doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.LG","eess.IV","physics.med-ph"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2501.01908","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2509.07936","title":"Feature Space Analysis by Guided Diffusion Model","year":2026,"authors":["Kimiaki Shirahama","Kaduki Yamashita","Miki Yanobu"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2509.07936","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2511.03192","title":"SAIPAS: Simulating aspect-angles-invariant physical adversarial attacks on SAR target recognition models","year":2026,"authors":["Isar Lemeire","Yee Wei Law","Sang-Heon Lee"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2511.03192","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2605.14285","title":"ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing","year":2026,"authors":["Yixuan Jia","Siyi Chen","Yida Pan"],"author_count":12,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.LG"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2605.14285","fulltext_endpoint":"/api/document/arxiv-2605.14285/fulltext","references_endpoint":null},{"id":"arxiv-2609.25597","title":"Observer Choice and Threshold Selection in Retinal Vessel Segmentation: A Subject-Separated Evaluation","year":2026,"authors":["Wenhao Xu","Yixian Kong","Ting Pan"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.25597","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.06602","title":"Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable $T_{1ρ}$ and $T_2$ Quantification Without High-Resolution Morphological Images","year":2026,"authors":["Ahmed Tahseen Minhaz","Richard Lartey","Zhiyuan Zhang"],"author_count":11,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.06602","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.25685","title":"Initialization and Stopping Tolerance in CPU Dermoscopic Segmentation","year":2026,"authors":["Wenhao Xu","Yixian Kong","Ting Pan"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.25685","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.07576","title":"CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan?","year":2026,"authors":["Kevin Lee"],"author_count":1,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.LG","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.07576","fulltext_endpoint":"/api/document/arxiv-2610.07576/fulltext","references_endpoint":null},{"id":"arxiv-2610.07561","title":"LARK: A Low-Cost, Accurate, Occlusion-Resilient, Kalman Filter-Assisted Tracking System for Image-Guided Surgery","year":2026,"authors":["George Sideris","Justin Cree","Andrew Stirling"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.07561","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.08080","title":"Laplace-Domain Beamforming for Ultrafast Plane-Wave Imaging","year":2026,"authors":["Martin F. Schiffner"],"author_count":1,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["physics.med-ph","eess.IV","eess.SP"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.08080","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.07884","title":"Learned Adaptive Multiresolution Diffusion Imaging","year":2026,"authors":["Christian Tantardini","Stig Rune Jensen","Roberto Di Remigio Eikås"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["math.NA","cs.LG","cs.NA","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.07884","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.08213","title":"RACE-FPP: A Robust AI-assisted Characterisation Enhancement for Fringe Projection Profilometry","year":2026,"authors":["Osman Ali","Xiangjun Kong","Tibebe Yalew"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV","physics.optics"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.08213","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-1907.09194","title":"Research on Deep Learning-Based Semantic Segmentation Algorithms for Subcortical Brain Structures","year":2026,"authors":["Binbin Yang","Weiwei Zhang"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-1907.09194","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2603.21911","title":"A Variational Latent-Space Framework for Uncertainty-Aware Spectral Image Emulation","year":2026,"authors":["Chedly Ben Azizi","Claire Guilloteau","Gilles Roussel"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.LG","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2603.21911","fulltext_endpoint":"/api/document/arxiv-2603.21911/fulltext","references_endpoint":null},{"id":"arxiv-2610.00678","title":"Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation","year":2026,"authors":["Duong M. Nguyen","Trong Nghia Hoang","Hang Thi Nguyen"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.LG"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.00678","fulltext_endpoint":"/api/document/arxiv-2610.00678/fulltext","references_endpoint":null},{"id":"arxiv-2610.08838","title":"Deep Learning for Longitudinal Medical Imaging: A Scoping Review","year":2026,"authors":["Francesca Mussa","Divyanshu Tak","Atlas H. Avval"],"author_count":8,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.08838","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.08843","title":"Optimization of Deep Learning Model for Denoising Dose Profiles in Proton Therapy","year":2026,"authors":["Junaid Jawaid","Matteo Spezialetti","Gabriele Libardi"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["q-bio.QM","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.08843","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.08848","title":"STRIDE: Spatial-Temporal Representation for Interval-conditioned Disease Evolution in Longitudinal Glioblastoma MRI","year":2026,"authors":["Wenhao Guo","Changchang Yin","Pierre Giglio"],"author_count":6,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.08848","fulltext_endpoint":"/api/document/arxiv-2610.08848/fulltext","references_endpoint":null},{"id":"arxiv-2610.08849","title":"Abdominal Ultrasound Simulation from Semantic Labels using Paired Label-to-Physics-Based Image Translation","year":2026,"authors":["Santiago Vitale","Duilio Deangeli","Ignacio Larrabide"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.08849","fulltext_endpoint":"/api/document/arxiv-2610.08849/fulltext","references_endpoint":null},{"id":"arxiv-2610.08866","title":"Geometry-Aware Diffusion Approximate Posterior Sampling for Sparse-View and Limited-Angle CT","year":2026,"authors":["Honglei Brinkmann","Carola-Bibiane Schönlieb","Ander Biguri"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.LG"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.08866","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.08892","title":"Hybrid++: The Bridge between PDE Models and Deep Learning for Gamma Noise Removal","year":2026,"authors":["Mahipal Jetta","Sujato Dutta"],"author_count":2,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.AI"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.08892","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.09098","title":"On-Device Super-Resolution Imaging for a Low-Cost SPAD Array on a 640-KB-SRAM Microcontroller","year":2026,"authors":["Zhenya Zang","Istvan Gyongy","Mike Davies"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.09098","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.09957","title":"Diagnosing Diversity Collapse and Validating Mask-Conditioned Diffusion for Labeled Microtubule Microscopy","year":2026,"authors":["Mario Koddenbrock","Frederic Rapp","Simone Reber"],"author_count":4,"journal":"Proceedings of Machine Learning Research (PMLR)2027","doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.09957","fulltext_endpoint":"/api/document/arxiv-2610.09957/fulltext","references_endpoint":null},{"id":"arxiv-2610.10264","title":"CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing","year":2026,"authors":["William Chen","Prem Seetharaman","Ke Chen"],"author_count":13,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.SD","eess.AS","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.10264","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-688e9fe501a1c5e8710b","title":"Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images","year":2022,"authors":["Sk Imran Hossain","Jocelyn de Goër de Herve","Md Shahriar Hassan"],"author_count":19,"journal":"Computer Methods and Programs in Biomedicine, Volume 215, 2022, 106624, ISSN 0169-2607","doi":"10.1016/j.cmpb.2022.106624","source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV","cs.LG"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-688e9fe501a1c5e8710b","fulltext_endpoint":null,"references_endpoint":null},{"id":"doi-c682e6a733ee27d1d046","title":"Expert Opinion Elicitation for Assisting Deep Learning based Lyme Disease Classifier with Patient Data","year":2022,"authors":["Sk Imran Hossain","Jocelyn de Goër de Herve","David Abrial"],"author_count":9,"journal":"International Journal of Medical Informatics, Volume 193, 2025, 105682, ISSN 1386-5056","doi":"10.1016/j.ijmedinf.2024.105682","source":"arxiv","topics":["image-video-processing"],"keywords":["cs.AI","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/doi-c682e6a733ee27d1d046","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2506.16556","title":"VesselSDF: Distance Field Priors for Vascular Network Reconstruction","year":2026,"authors":["Salvatore Esposito","Daniel Rebain","Arno Onken"],"author_count":5,"journal":"International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2025","doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2506.16556","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2510.13422","title":"Distribution-Aligned Representation Adaptation for DJSCC over Hybrid Wireless-Wired Networks","year":2026,"authors":["Jiangyuan Guo","Wei Chen","Yuxuan Sun"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["information-theory","image-video-processing"],"keywords":["eess.IV","cs.IT","math.IT"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2510.13422","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2602.23833","title":"Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning","year":2026,"authors":["Tuan Truong","Melanie Dohmen","Sara Lorio"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2602.23833","fulltext_endpoint":"/api/document/arxiv-2602.23833/fulltext","references_endpoint":null},{"id":"arxiv-2607.08033","title":"SCI-Mamba: Unsupervised Learning based Low-Light Image Enhancement for Non-Cooperative Spacecraft","year":2026,"authors":["Yiyong Sun","Weihang Shan","Shijun Wei"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2607.08033","fulltext_endpoint":"/api/document/arxiv-2607.08033/fulltext","references_endpoint":null},{"id":"doi-001c8eaafb77cf598b40","title":"E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference","year":2026,"authors":["Ankit Kumar Tenwar","Mukul Lokhande","Santosh Kumar Vishvakarma"],"author_count":3,"journal":"2026 30th International Symposium on VLSI Design and Test (VDAT)","doi":"10.1109/vdat72243.2026.11704590","source":"arxiv","topics":["image-video-processing"],"keywords":["cs.NE","cs.AR","cs.CV","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/doi-001c8eaafb77cf598b40","fulltext_endpoint":"/api/document/doi-001c8eaafb77cf598b40/fulltext","references_endpoint":null},{"id":"arxiv-2609.08081","title":"Reliability assessment and multicenter clinical application of magnetic resonance methods for knee cartilage quantification","year":2026,"authors":["Binbin Yang","Yongmei Jian","Chenglei Liu"],"author_count":13,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","q-bio.QM"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.08081","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2609.19730","title":"The segmentation ceiling: why explicit left-ventricular masks do not improve learned ejection-fraction regression","year":2026,"authors":["Farshid Farhadi Khouzani","Paul La Plante","Bryar Mustafa Shareef"],"author_count":4,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV","cs.CV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2609.19730","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.11036","title":"Adapting Appearance-Based Gaze Estimation to Narrow-Range, Long-Duration Screen Viewing","year":2026,"authors":["Jordan Prescott","Kleanthis Avramidis","Shrikanth Narayanan"],"author_count":3,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.11036","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.11104","title":"Skeleton-Guided Progressive Test-Time Adaptation for Thin Curvilinear Structures","year":2026,"authors":["Boa Jang","JunGyu Lee","Gwanho Lee"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC-BY-4.0","has_fulltext":true,"has_references":false,"rights_class":"licensed_content","access":"paid","version":2,"content_endpoint":"/api/document/arxiv-2610.11104","fulltext_endpoint":"/api/document/arxiv-2610.11104/fulltext","references_endpoint":null},{"id":"arxiv-2610.11144","title":"Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery","year":2026,"authors":["Jingbo Yue","Bruce Coburn","Jinge Ma"],"author_count":5,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","cs.AI","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.11144","fulltext_endpoint":null,"references_endpoint":null},{"id":"arxiv-2610.11149","title":"A Unified Score Matching Paradigm for Video Anomaly Detection and Anticipation","year":2026,"authors":["Congqi Cao","Zhenhe Liang","Hanwen Zhang"],"author_count":7,"journal":null,"doi":null,"source":"arxiv","topics":["image-video-processing"],"keywords":["cs.CV","eess.IV"],"license":"CC0-1.0","has_fulltext":false,"has_references":false,"rights_class":"metadata_only","access":"paid","version":1,"content_endpoint":"/api/document/arxiv-2610.11149","fulltext_endpoint":null,"references_endpoint":null}]}