Sign in

TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning

By Andrea Ziani and others
We introduce TempCLR, a new time-coherent contrastive learning approach for the structured regression task of 3D hand reconstruction. Unlike previous time-contrastive methods for hand pose estimation, our framework considers temporal consistency in its augmentation scheme, and accounts for the differences of hand poses along the temporal direction. Our data-driven method... Show more
September 1, 2022
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning
Click on play to start listening