Learning Compact Representations for LiDAR Completion and Generation

Figure 1. UltraLiDAR learns discrete representations from large-scale LiDAR point clouds and conduct realistic, scalable and controllable LiDAR completion and generation. Top row: Sparse-to-dense LiDAR completion; Second row: Controllable manipulation of real LiDAR with actor removal and insertion; Third row: Diverse LiDAR generation with realistic global structure and fine-grained details; Bottom row: Conditional scene generation with partially observed point clouds (highlighted in red). Please see supp. for more examples.