arXiv preprint / 6D位姿

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

作者：Haosong Peng, Hao Li, Yalun Dai, Yushi Lan, Yihang Luo, Tianyu Qi, Zhengshen Zhang, Yufeng Zhan, Junfei Zhang, Wenchao Xu, Ziwei Liu HKUST, NTU, SYSU, NUS, Alibaba Group · 单位：HKUST NTU SYSU NUS Alibaba Group · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2025-11-14

6D位姿估计
新标签打开 AlphaXiv新标签打开 Project
OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer figure
AlphaXiv 中文概览（可滚动查看）