Papers › SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced...

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

19 Aug 2024arXiv:2408.10037archive 2025-07-28

Wiktor Mucha, Michael Wray, Martin Kampel

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.

PaperPDFCode

Code

wiktormucha/SHARP officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Hand Pose EstimationAction RecognitionDepth EstimationHand Pose EstimationObject DetectionPose EstimationSkeleton Based Action Recognitionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition H2O (2 Hands and Objects) SHARP Actions Top-1 91.73 #2 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SHARP Hand Pose 3D #2 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SHARP Object Label Yes #2 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SHARP Object Pose 2D #2 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SHARP RGB No #2 of 11 Archive leaderboard report
Skeleton Based Action Recognition H2O (2 Hands and Objects) SHARP Accuracy 91.73 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections