LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

Sijin Chen, Xin Chen, Chi Zhang, Mingsheng Li, Gang Yu, Hao Fei, Hongyuan Zhu, Jiayuan Fan, Tao Chen
Jan 3, 2024
Go to Project Site Paper GitHub Arxiv Project Cite GitHub stars
Example of 3D dense captioning.
Type
Conference paper
Mm 2024 Selected
Xin Chen
Xin Chen
陈欣 | Research Scientist

My research interests include generative AI, human agents, 3D and human motion generation.