Object Pose Estimation via the Aggregation of Diffusion Features

arXiv:2403.18791v1 Announce Type: new
Abstract: Estimating the pose of objects from images is a crucial task of 3D scene understanding, and recent approaches have shown promising results on very large benchmarks. However, these methods experience a significant performance drop when dealing with unseen objects. We believe that it results from the limited generalizability of image features. To address this problem, we have an in-depth analysis on the features of diffusion models, e.g. Stable Diffusion, which hold substantial potential for modeling …

aggregation arxiv cs.cv diffusion features object type via