arXiv preprint / 6D位姿

Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation

作者：Ken Deng, Yifu Qiu, Yoni Kasten, Shay B. Cohen, NVIDIA Research, @ed.ac.uk, @nvidia.com, y.ziser@rug.nl · 单位：University of Edinburgh University of Oxford, NVIDIA Research University of Groningen · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2026-01-29

6D位姿估计相机位姿
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation figure
AlphaXiv 中文概览（可滚动查看）