Papers › TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation

TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation

14 Jun 2022arXiv:2206.07117archive 2025-07-28

Mohammad Rezaei, Razieh Rastgoo, Vassilis Athitsos

3D hand pose estimation methods have made significant progress recently. However, the estimation accuracy is often far from sufficient for specific real-world applications, and thus there is significant room for improvement. This paper proposes TriHorn-Net, a novel model that uses specific innovations to improve hand pose estimation accuracy on depth images. The first innovation is the decomposition of the 3D hand pose estimation into the estimation of 2D joint locations in the depth image space (UV), and the estimation of their corresponding depths aided by two complementary attention maps. This decomposition prevents depth estimation, which is a more difficult task, from interfering with the UV estimations at both the prediction and feature levels. The second innovation is PixDropout, which is, to the best of our knowledge, the first appearance-based data augmentation method for hand depth images. Experimental results demonstrate that the proposed model outperforms the state-of-the-art methods on three public benchmark datasets. Our implementation is available at https://github.com/mrezaei92/TriHorn-Net.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mrezaei92/TriHorn-Net officialmentioned in papermentioned 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 EstimationData AugmentationDepth EstimationHand Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hand Pose Estimation ICVL Hands TriHorn-Net Average 3D Error 5.73 #2 of 15 Archive leaderboard report
Hand Pose Estimation MSRA Hands TriHorn-Net Average 3D Error 7.13 #1 of 11 Archive leaderboard report
Hand Pose Estimation NYU Hands TriHorn-Net Average 3D Error 7.68 #3 of 17 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