KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

Tomas Jakab
Jiajun Wu
Angjoo Kanazawa
Computer Vision and Pattern Recognition (CVPR) (2021)

Abstract

We present KeypointDeformer, a novel unsupervised method for shape control through automatically discovered 3D keypoints. Our approach produces intuitive and semantically consistent control of shape deformations. Moreover, our discovered 3D keypoints are consistent across object category instances despite large shape variations. Since our method is unsupervised, it can be readily deployed to new object categories without requiring expensive annotations for 3D keypoints and deformations.

Research Areas