Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition

About

Hand pose represents key information for action recognition in the egocentric perspective, where the user is interacting with objects. We propose to improve egocentric 3D hand pose estimation based on RGB frames only by using pseudo-depth images. Incorporating state-of-the-art single RGB image depth estimation techniques, we generate pseudo-depth representations of the frames and use distance knowledge to segment irrelevant parts of the scene. The resulting depth maps are then used as segmentation masks for the RGB frames. Experimental results on H2O Dataset confirm the high accuracy of the estimated pose with our method in an action recognition task. The 3D hand pose, together with information from object detection, is processed by a transformer-based action recognition network, resulting in an accuracy of 91.73%, outperforming all state-of-the-art methods. Estimations of 3D hand pose result in competitive performance with existing methods with a mean pose error of 28.66 mm. This method opens up new possibilities for employing distance information in egocentric 3D hand pose estimation without relying on depth sensors.

Wiktor Mucha, Michael Wray, Martin Kampel• 2024

Related benchmarks

TaskDatasetResultRank
Action RecognitionH2O (test)
Accuracy91.73
26
3D Hand Pose EstimationH2O
MPJPE Right27.02
14
3D Hand Pose EstimationH2O (same-domain)
MPJPE28.66
8
Egocentric 3D Hand Pose EstimationAssemblyHands
MPJPE-RA103.8
7
Egocentric 3D Hand Pose EstimationEpic-Kps
L2 Error14.41
7
Showing 5 of 5 rows

Other info

Code

Follow for update