HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation ofHands and Object in Interaction
HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation ofHands and Object in Interaction
Shreyas Hampali,Sayan Deb Sarkar,Mahdi Rad,V. Lepetit
2021 · DBLP: journals/corr/abs-2104-14639
arXiv.org · 15 Citations
TLDR
A robust and accurate method for estimating the 3D poses of two hands in close interaction from a single color image, which al-lies the recognition power of a Transformer to the accuracy of heatmap-based methods.