3 papers
cs.CV2026
PhysFlow: Physics-Aware Optical Flow for Motion Controllable Video Generation
Cong Wang, Hanxin Zhu, Yonglin Tian +5
Video generation models have recently attracted substantial attention for their ability to generate visually compelling videos, yet ensuring physically consistent and plausible dyn…
cs.CV2024
Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding
Yuhang Liu, Boyi Sun, Guixu Zheng +3
LiDAR sensors play a crucial role in various applications, especially in autonomous driving. Current research primarily focuses on optimizing perceptual models with point cloud dat…
cs.CV2024
3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving
Boyi Sun, Yuhang Liu, Xingxia Wang +3
Point cloud data labeling is considered a time-consuming and expensive task in autonomous driving, whereas annotation-free learning training can avoid it by learning point cloud re…