3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days. Unlike 2D images that are projective observations of the environment, 3D models provide metric reconstruction of the scenes without occlusion or scale ambiguity. In this paper, we define "3D occupancy size", as the number of voxels occupied by each instance. It owns advantages of robustness in prediction, on which basis, OccuSeg, an occupancy-aware 3D instance segmentation scheme is proposed. Our multi-task learning produces both occupancy signal and embedding representations, where the training of spatial and feature embeddings varies with their difference in scale-aware. Our clustering scheme benefits from the reliable comparison between the predicted occupancy size and the clustered occupancy size, which encourages hard samples being correctly clustered and avoids over segmentation. The proposed approach achieves state-of-the-art performance on 3 real-world datasets, i.e. ScanNetV2, S3DIS and SceneNN, while maintaining high efficiency.
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；Centre for Artificial Intelligence and Robotics, HKISI, CAS（中国科学院香港创新研究院人工智能与机器人创新中心）
Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology（东方理工大学）；Shanghai Jiao Tong University（上海交通大学）；Wuhan University（武汉大学）；Great Wall Motor（长城汽车）；Tsinghua University（清华大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）
Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference
National Institute of Standards and Technology（美国国家标准与技术研究院）；Colorado State University（科罗拉多州立大学）；Applied Research Associates（应用研究联合公司）；US Army CCDC Ground Vehicle Systems Center（美国陆军作战能力发展司令部地面车辆系统中心）
SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark
IEE S.A（IEE公司）；DFKI - German Research Center for Artificial Intelligence（德国人工智能研究中心）；University of Kaiserslautern（凯泽斯劳滕大学）；Trier University of Applied Sciences（特里尔应用技术大学）
Closed-Circuit Television Data as an Emergent Data Source for Urban Rail Platform Crowding Estimation
Massachusetts Institute of Technology（麻省理工学院）；Washington Metropolitan Area Transit Authority（华盛顿特区公共交通局）；Department of Urban Studies and Planning（城市研究与规划系）
Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation
School of Aeronautic Engineering, Changsha University of Science and Technology（长沙理工大学航空工程学院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；School of Automation, Central South University（中南大学自动化学院）；University of British Columbia（不列颠哥伦比亚大学）
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
ISIR, Sorbonne Université（索邦大学ISIR研究所）；Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague（布拉格捷克理工大学捷克信息学、机器人学与控制论研究所）；FEE CTU（捷克技术大学电气工程系）；CIIRC CTU（捷克技术大学捷克信息学、机器人学与控制论研究所）；Kyutai（Kyutai公司）；LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS（法国国家科学研究中心-古斯塔夫·埃菲尔大学巴黎路桥学院LIGM实验室）
Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban Environments
Stanford University（斯坦福大学）
移动障碍物的检测和分割，以及对本地环境未来占用状态的预测，对于自动驾驶汽车主动做出安全和明智的决策至关重要。在本文中，我们提出了一个框架，使用深度神经网络架构将这两种功能集成在一起。我们的方法首先检测和分割场景中的移动对象，并使用这些信息来预测自动驾驶汽车周围环境的时空演变。为了解决静态-动态对象分割和环境预测模型直接集成的问题，我们建议在整个框架中使用基于占用的环境表示。我们的方法在真实世界的Waymo Open Dataset上进行了验证，并显示出比基线方法更高的预测准确性。
MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models
Center of Excellence in Precision Medicine and Digital Health, Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand（精准医学与数字健康中心，朱拉隆功大学牙科学院，泰国曼谷）；Department of Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan（计算机工程系，COMSATS伊斯兰堡大学，巴基斯坦伊斯兰堡）；School of Biomedical Engineering, UNSW, Sydney, NSW, Australia（生物医学工程学院，新南威尔士大学，澳大利亚悉尼，新南威尔士）；Visiting Scholar (Collaborative Projects), Center of Excellence in Precision Medicine and Digital Health, Chulalongkorn University, Bangkok, Thailand（访问学者（合作项目），精准医学与数字健康中心，朱拉隆功大学，泰国曼谷）；Department of Computing, Abasyn University Islamabad Campus (AUIC), Islamabad, Pakistan（计算系，阿巴斯扬大学伊斯兰堡校区（AUIC），巴基斯坦伊斯兰堡）；Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates（Mohamed bin Zayed人工智能大学，阿布扎比，阿拉伯联合酋长国）；College of Computer and Information Sciences, prince Sultan University, Riyadh, SAudi Arabia（计算机与信息科学学院，苏丹王子大学，沙特阿拉伯利雅得）
