3D Hand Pose Estimation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

20 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 87 papers with code (178 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• End-to-end Recovery of Human Shape and Pose
  18 Dec 2017 10 repositories listed
  The main objective is to minimize the reprojection loss of keypoints, which allow our model to be trained using images in-the-wild that only have ground truth 2D annotations.
• Learning to Estimate 3D Hand Pose from Single RGB Images
  3 May 2017 8 repositories listed
  Low-cost consumer depth cameras and deep learning have enabled reasonable 3D hand pose estimation from single depth images.
• FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
  24 Mar 2023 6 repositories listed Syntology ran 1 of 5 samples · 4 unverified · 5 pointer-only (licence)
  To this end, we introduce a novel token mixing operator, RepMixer, a building block of FastViT, that uses structural reparameterization to lower the memory access cost by removing skip-connections in the network.
• V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map
  20 Nov 2017 5 repositories listed
  To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel likelihood…
• Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
  4 Apr 2020 4 repositories listed Syntology ran 6 of 20 samples · 14 unverified
  We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh…
• HOnnotate: A method for 3D Annotation of Hand and Object Poses
  2 Jul 2019 4 repositories listed
  This dataset is currently made of 77, 558 frames, 68 sequences, 10 persons, and 10 objects.
• DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation
  28 Aug 2017 4 repositories listed
  DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map.
• Mesh Graphormer
  1 Apr 2021 3 repositories listed
  We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image.
• Learning joint reconstruction of hands and manipulated objects
  11 Apr 2019 3 repositories listed
  Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation.
• Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
  7 Mar 2024 2 repositories listed Syntology ran 10 of 16 samples · 6 unverified · 16 pointer-only (licence)
  These two stereo constraints are used in a complementary manner to generate pseudo-labels, allowing reliable adaptation.
• ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
  12 Sep 2021 2 repositories listed
  In contrast, data synthesis can easily ensure those diversities separately.
• PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning
  10 Jun 2021 2 repositories listed
  Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation.
• DexYCB: A Benchmark for Capturing Hand Grasping of Objects
  9 Apr 2021 2 repositories listed
  We introduce DexYCB, a new dataset for capturing hand grasping of objects.
• HandTailor: Towards High-Precision Monocular 3D Hand Recovery
  18 Feb 2021 2 repositories listed
  3D hand pose estimation and shape recovery are challenging tasks in computer vision.
• InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image
  21 Aug 2020 2 repositories listed
  Therefore, we firstly propose (1) a large-scale dataset, InterHand2.
• Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose
  20 Aug 2020 2 repositories listed
  Most of the recent deep learning-based 3D human pose and mesh estimation methods regress the pose and shape parameters of human mesh models, such as SMPL and MANO, from an input image.
• Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
  8 May 2019 2 repositories listed Syntology ran 2 of 7 samples · 5 unverified
  Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location.
• 3D Hand Shape and Pose Estimation from a Single RGB Image
  3 Mar 2019 2 repositories listed
  This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image.
• End-to-end Hand Mesh Recovery from a Monocular RGB Image
  25 Feb 2019 2 repositories listed
  In this paper, we present a HAnd Mesh Recovery (HAMR) framework to tackle the problem of reconstructing the full 3D mesh of a human hand from a single RGB image.
• 3D Hand Shape and Pose from Images in the Wild
  9 Feb 2019 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We present in this work the first end-to-end deep learning based method that predicts both 3D hand shape and pose from RGB images in the wild.
• Monocular 3D Hand Pose Estimation with Implicit Camera Alignment
  10 Jun 2025 1 repository listed
  Estimating the 3D hand articulation from a single color image is a continuously investigated problem with applications in Augmented Reality (AR), Virtual Reality (VR), Human-Computer Interaction (HCI), and robotics.
• Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation
  25 Mar 2025 1 repository listed Syntology ran 6 of 6 samples · 0 unverified · 6 pointer-only (licence)
  We demonstrate that synthetic hand data can achieve the same level of accuracy as real data when integrating our identified components, paving the path to use synthetic data alone for hand pose estimation.
• SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training
  21 Feb 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We present a framework for pre-training of 3D hand pose estimation from in-the-wild hand images sharing with similar hand characteristics, dubbed SimHand.
• WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
  18 Sep 2024 1 repository listed
  In recent years, 3D hand pose estimation methods have garnered significant attention due to their extensive applications in human-computer interaction, virtual reality, and robotics.
• SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition
  19 Aug 2024 1 repository listed
  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.
• HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation
  30 Jul 2024 1 repository listed
  To address this challenge, this paper proposes the Denoising Adaptive Graph Transformer, HandDAGT, for hand pose estimation.
• AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild
  25 Jul 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  To overcome these issues, we propose AttentionHand, a novel method for text-driven controllable hand image generation.
• Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
  12 Jul 2024 1 repository listed Syntology ran 7 of 11 samples · 4 unverified · 11 pointer-only (licence)
  Specifically, we design a Graph-guided State Space (GSS) block that learns the graph-structured relations and spatial sequences of joints and uses 88.
• HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud
  4 Apr 2024 1 repository listed Syntology ran 2 of 3 samples · 1 unverified
  Extracting keypoint locations from input hand frames, known as 3D hand pose estimation, is a critical task in various human-computer interaction applications.
• HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions
  27 Mar 2024 1 repository listed Syntology ran 10 of 10 samples · 0 unverified
  Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.