This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation dataset. Unlike Trans10K-v1 that only has two limited categories, our new dataset has several appealing benefits. (1) It has 11 fine-grained categories of transparent objects, commonly occurring in the human domestic environment, making it more practical for real-world application. (2) Trans10K-v2 brings more challenges for the current advanced segmentation methods than its former version. Furthermore, a novel transformer-based segmentation pipeline termed Trans2Seg is proposed. Firstly, the transformer encoder of Trans2Seg provides the global receptive field in contrast to CNN's local receptive field, which shows excellent advantages over pure CNN architectures. Secondly, by formulating semantic segmentation as a problem of dictionary look-up, we design a set of learnable prototypes as the query of Trans2Seg's transformer decoder, where each prototype learns the statistics of one category in the whole dataset. We benchmark more than 20 recent semantic segmentation methods, demonstrating that Trans2Seg significantly outperforms all the CNN-based methods, showing the proposed algorithm's potential ability to solve transparent object segmentation.
University of Warwick（华威大学）；NRP Co.（NRP公司）；Royal Wolverhampton NHS Trust（皇家伍尔弗汉普顿NHS信托）；University of Sheffield（谢菲尔德大学）；University Hospitals Coventry and Warwickshire（考文垂和沃里克郡大学医院）
Anabranch Network for Camouflaged Object Segmentation
University of Dayton（代顿大学）；Institute of Industrial Science, the University of Tokyo（东京大学生产技术研究所）；The Graduate University for Advanced Studies (SOKENDAI)（综合研究大学院大学）；University of Science, VNU-HCM（越南国立大学胡志明市分校科学大学）；National Institute of Informatics（国立信息学研究所）
Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections
College of Computer Science and Engineering, Shandong University of Science and Technology（山东科技大学计算机科学与工程学院）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）
提出基于3D Gaussian Splatting的交互式分割方法Seg-Wild，通过多维特征嵌入和Spiky 3D Gaussian Cutter处理无约束图像中的瞬态遮挡，实现更优的野外场景分割与重建质量。
Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所）；School of Information Science and Technology, Shijiazhuang Tiedao University（石家庄铁道大学信息科学与技术学院）；D-Robotics（杭州宇树科技有限公司）
Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion
The Hong Kong University of Science and Technology（香港科学与技术大学）；CFAR & IHPC, A*STAR（CFAR与IHPC，A*STAR）；Deakin University（德克萨斯大学）；Nankai University（南开大学）；National University of Singapore（新加坡国立大学）；Trinity College Dublin（都柏林大学）
