Feb 2, 2023 · We propose a self-supervised learning framework, HaMuCo, that learns a single-view hand pose estimator from multi-view pseudo 2D labels.

To alleviate the label-hungry limitation, we propose a self- supervised learning framework, HaMuCo, that learns a single-view hand pose estimator from multi- ...

We propose a self-supervised learning framework, HaMuCo, that learns a single view hand pose estimator from multi-view pseudo 2D labels.

HaMuCo is a multi-view self-supervised 3D hand pose estimation method that only requires 2D pseudo labels for training.

We propose the first self-supervised learning frame- work for single-view hand pose estimation without any training data annotation and achieve state-of-the-art.

We propose a self-supervised learning framework, HaMuCo, that learns a single-view hand pose estimator from multi-view pseudo 2D labels.

Duration: 4:56
Posted: Sep 27, 2023

In Fig. 10, we visualize the hand pose estimation results in PA-MPJPE for each grasp classes (left). The baseline achieves high accuracy across all grasp ...

README.md · Issues 4 · Pull requests 1

Recent advancements in 3D hand pose estimation have shown promising results, but its effectiveness has primarily relied on the availability of large-scale ...