3 papers
cs.CV2025
MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
Ruibing Hou, Mingshuang Luo, Hongyu Pan +2
This paper proposes MotionVerse, a unified framework that harnesses the capabilities of Large Language Models (LLMs) to comprehend, generate, and edit human motion in both single-p…
cs.CV2022
INT: Towards Infinite-frames 3D Detection with An Efficient Framework
Jianyun Xu, Zhenwei Miao, Da Zhang +7
It is natural to construct a multi-frame instead of a single-frame 3D detector for a continuous-time stream. Although increasing the number of frames might improve performance, pre…
cs.CV2022
CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation
Xiaoyan Li, Gang Zhang, Hongyu Pan +1
LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-…