arXiv AI By Xiao Lin, Minghao Zhu, Yun Peng, Liuyi Wang, Qiyi Wang, Chengju Liu, Qijun Chen

MemPose: Category-level Object Pose Estimation with Memory

Read the original on arXiv AI →

arXiv:2607. 04930v1 Announce Type: cross Abstract: In the pursuit of robust and generalizable category-level object pose estimation, most existing methods adopt parametric formulations that learn effective representations from data, yet they primarily encode category-level patterns into fixed shape priors or static parameter weights, which limits their scalability to highly diverse instances.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Jul 6

MemPose: Category-level Object Pose Estimation with Memory

In the pursuit of robust and generalizable category-level object pose estimation, most existing methods adopt parametric formulations that learn effective representations from data, yet they primarily encode category-level patterns into fixed shape priors or static parameter weights, which limits their scalability to highly diverse instances. In this paper, we rethink category-level pose estimation from a memory-centric perspective and present MemPose, a memory-augmented framework that explicitly incorporates category-level geometric memory into the pose estimation pipeline.