2 papers
cs.CV2026
Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction
Xiaoyan Liu, Jiaxin Liu, Kangrui Li +1
Current 4D generation paradigms are often bottlenecked by a sequential decoupling design: video is generated first, followed by 3D reconstruction, leading to high interaction laten…
cs.CV2023
MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer
Yongxin Shao, Aihong Tan, Binrui Wang +4
LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds.…