arXiv preprint / 6D位姿

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models

作者：Pablo Acuaviva, pablo.acuavivahuertos@unibe.ch, &Aram Davtyan 1 1, aram.davtyan@unibe.ch · 单位：Computer Vision Group, University of Bern — VITA Lab, EPFL — · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2025-06-10

6D位姿估计
新标签打开 AlphaXiv新标签打开 Project
From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models figure
AlphaXiv 中文概览（可滚动查看）