TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning. (arXiv:2209.00489v1 [cs.CV])

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
leverages unlabelled videos and a standard CNN, without relying on synthetic
data, pseudo-labels, or specialized architectures. Our approach improves the
performance of fully-supervised hand reconstruction methods by 15.9% and 7.6% …

arxiv learning time