Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images
机构 * Yonsei University（延世大学）
Comments Accepted to ICCV 2025. 10 pages main text, 4 figures, 4 tables, supplementary material included
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment
机构 * Technical University of Denmark（技术大学）
Comments Accepted to ICCV 2025 Workshop LIMIT
IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising
机构 * Department of Computer Science, Hanyang University（翰阳大学计算机科学系） ； School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）
Comments ICCV 2025. Project Page: https://dongjinkim9.github.io/projects/idf/
Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
机构 * University of Southern California（南加州大学）
Comments To be published in Explainable Computer Vision: Quo Vadis? workshop at ICCV'25
HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID
机构 * Department of Computer Science and Engineering, Michigan State University（密歇根州立大学计算机科学与工程系） ； Department of Computer Science, Drexel University（德雷塞尔大学计算机科学系）
Comments Published at ICCV 2025
TAGS: 3D Tumor-Adaptive Guidance for SAM
机构 * Southern University of Science and Technology（南方科技大学） ； Northwestern University（西北大学）
Comments Accepted by ICCV-APAH
