MOSIV: Multi-Object System Identification from Videos

"identify multi-object geometry and physics from video"

Chunjiang Liu, Xiaoyuan Wang, Qingran Lin, Albert Xiao, Haoyu Chen, Shizheng Wen, Hao Zhang, Lu Qi, Ming-Hsuan Yang, Laszlo A. Jeni, Min Xu, Yizhou Zhao

International Conference on Learning Representations (ICLR), 2026