AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViT

no code implementations • 15 Sep 2023 • Fangbo Qin, Taogang Hou, Shan Lin, Kaiyuan Wang, Michael C. Yip, Shan Yu

Towards flexible object-centric visual perception, we propose a one-shot instance-aware object keypoint (OKP) extraction approach, AnyOKP, which leverages the powerful representation ability of pretrained vision transformer (ViT), and can obtain keypoints on multiple object instances of arbitrary category after learning from a support image.

Object