Point Cloud
Point clouds are collections of 3D data points representing objects or scenes, primarily used for tasks like 3D reconstruction, object recognition, and autonomous navigation. Current research focuses on improving the efficiency and robustness of point cloud processing, employing techniques like deep learning (e.g., transformers, convolutional neural networks), optimal transport, and Gaussian splatting for tasks such as registration, completion, and compression. These advancements are crucial for applications ranging from robotics and autonomous driving to medical imaging and cultural heritage preservation, enabling more accurate and efficient analysis of complex 3D data.
1270papers
Papers - Page 55
November 29, 2022
November 28, 2022
November 25, 2022
November 23, 2022
November 22, 2022
November 20, 2022
GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds
Jiahao Nie, Zhiwei He, Yuxiang Yang, Mingyu Gao, Jing ZhangECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression
Yiqi Jin, Ziyu Zhu, Tongda Xu, Yuhuan Lin, Yan WangAdaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis
Shanshan Zhao, Mingming Gong, Xi Li, Dacheng Tao
November 19, 2022
November 18, 2022
November 17, 2022
ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection
Yiyang Shen, Rongwei Yu, Peng Wu, Haoran Xie, Lina Gong, Jing Qin, Mingqiang WeiEPCS: Endpoint-based Part-aware Curve Skeleton Extraction for Low-quality Point Clouds
Chunhui Li, Mingquan Zhou, Zehua Liu, Yuhe ZhangDexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation
Yuzhe Qin, Binghao Huang, Zhao-Heng Yin, Hao Su, Xiaolong Wang3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
Jiaheng Liu, Tong He, Honghui Yang, Rui Su, Jiayi Tian, Junran Wu, Hongcheng Guo, Ke Xu, Wanli OuyangYou Only Label Once: 3D Box Adaptation from Point Cloud to Image via Semi-Supervised Learning
Jieqi Shi, Peiliang Li, Xiaozhi Chen, Shaojie Shen