InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image
Not on the map. Why?
Abstract (arXiv)
Analysis of hand-hand interactions is a crucial step towards better understanding human behavior. However, most researches in 3D hand pose estimation have focused on the isolated single hand case. Therefore, we firstly propose (1) a large-scale dataset, InterHand2.6M, and (2) a baseline network, InterNet, for 3D interacting hand pose estimation from a single RGB image. The proposed InterHand2.6M consists of 2.6M labeled single and interacting hand frames under various poses from multiple subjects. Our InterNet simultaneously performs 3D single and interacting hand pose estimation. In our experiments, we demonstrate big gains in 3D interacting hand pose estimation accuracy when leveraging the interacting hand data in InterHand2.6M. We also report the accuracy of InterNet on InterHand2.6M, which serves as a strong baseline for this new dataset. Finally, we show 3D interacting hand pose estimation results from general images. Our code and dataset are available at https://mks0601.github.io/InterHand2.6M/.
Key facts. Cited by 244 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 20; 2022: 34; 2023: 60; 2024: 49; 2025: 38; 2026: 43.
244 papers.
Sort:
By area:
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
- 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
- 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
- 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
- 2023Reconstructing Hands in 3D with Transformerscited by 298
- 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
- 2024DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulationcited by 149
- 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 128
- 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
- 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 122
38 more
- 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
- 20243D Gaussian as a New Era: A Surveycited by 102
- 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 98
- 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
- 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
- 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
- 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 76
- 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
- 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
- 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
- 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
- 2026SAM 3D Body: Robust Full-Body Human Mesh Recoverycited by 61
- 2023SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understandingcited by 59
- 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 57
- 2024ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactionscited by 54
- 2023ContactGen: Generative Contact Modeling for Grasp Generationcited by 52
- 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
- 2024Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Cameracited by 50
- 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 48
- 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
- 2024Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Trackingcited by 46
- 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
- 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
- 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
- 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
- 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
- 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
- 2023Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wildcited by 36
- 2022Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videoscited by 35
- 2022Reconstructing Hand-Held Objects from Monocular Videocited by 35
- 2023A Dataset of Relighted 3D Interacting Handscited by 35
- 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
- 2023Learning Human-to-Robot Handovers from Point Cloudscited by 34
- 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 33
- 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 32
- 2024GigaHands: A Massive Annotated Dataset of Bimanual Hand Activitiescited by 32
- 2025SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimationcited by 31
- 2025InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generationcited by 31
50 most cited of 244 All 244 (JSON)
- 2026ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild28 Sep 2026
- 2026MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery9 Sep 2026
- 2026Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance Heritage3 Sep 2026
- 2026Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands12 Aug 2026
- 2026DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units4 Aug 2026
- 2026OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting31 Jul 2026
- 2026Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer30 Jul 2026
- 2026Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting17 Jul 2026
- 2026Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction15 Jul 2026
- 2026WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation7 Jul 2026
- 2026Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation1 Jul 2026
- 2026Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation29 Jun 2026
38 more
- 2026VEPHand: View-Efficient Photometric Hand Performance Capture at Scale14 Jun 2026
- 2026High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians14 Jun 2026
- 2026AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking20 May 2026
- 2026StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video18 May 2026
- 2026EgoEV-HandPose: Egocentric 3D Hand Pose Estimation and Gesture Recognition with Stereo Event Cameras12 May 2026
- 2026Training-Free Dense Hand Contact Estimation with Multi-Modal Large Language Models7 May 2026
- 2026EgoEMG: A Multimodal Egocentric Dataset with Bilateral EMG and Vision for Hand Pose Estimation7 May 2026
- 2026Tamaththul3D: High-Fidelity 3D Saudi Sign Language Avatars from Monocular Video6 May 2026
- 2026Robust Camera-to-Mocap Calibration and Verification for Large-Scale Multi-Camera Data Capture23 Apr 2026
- 2026Towards Multi-View Sign Language Understanding: A Benchmark Dataset and Baseline20 Apr 2026
- 2026HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments16 Apr 2026
- 2026ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets9 Apr 2026
- 2026Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors6 Apr 2026
- 2026HandDreamer: Zero-Shot Text to 3D Hand Model Generation using Corrective Hand Shape Guidance6 Apr 2026
- 2026HandX: Scaling Bimanual Motion and Interaction Generation30 Mar 2026
- 2026SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild30 Mar 2026
- 2026AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation26 Mar 2026
- 2026HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images25 Mar 2026
- 2026Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves21 Mar 2026
- 2026Gesture-Aware Pretraining and Token Fusion for 3D Hand Pose Estimation18 Mar 2026
- 2026Fast-HaMeR: Boosting Hand Mesh Reconstruction using Knowledge Distillation17 Mar 2026
- 2026Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator16 Mar 2026
- 2026SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment28 Feb 2026
- 2026WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos25 Feb 2026
- 2026WildGHand: Learning Anti-Perturbation Gaussian Hand Avatars from Monocular In-the-Wild Videos24 Feb 2026
- 2026SAM 3D Body: Robust Full-Body Human Mesh Recovery17 Feb 2026
- 2026AirGlove: Exploring Egocentric 3D Hand Tracking and Appearance Generalization for Sensing Gloves5 Feb 2026
- 2026EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning27 Jan 2026
- 2026Towards Egocentric 3D Hand Pose Estimation in Unseen Domains10 Jan 2026
- 2026DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation9 Jan 2026
- 2026FUSION: Full-Body Unified Motion Prior for Body and Hands via Diffusion7 Jan 2026
- 2025DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors24 Dec 2025
- 2025Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction18 Nov 2025
- 2025PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior7 Nov 2025
- 2025Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks4 Nov 2025
- 2025Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images7 Oct 2025
- 2025Ego-Exo 3D Hand Tracking in the Wild with a Mobile Multi-Camera Rig2 Oct 2025
- 2025Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale2 Oct 2025
50 newest of 244 All 244 (JSON)
- 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusioncited by 28
- 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clipscited by 15
- 2024HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Modelscited by 14
- 2023HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Modelscited by 13
- 2024Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generationcited by 13
- 2023DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Modelscited by 7
- 2023Denoising Diffusion for 3D Hand Pose Estimation from Imagescited by 2
- 2026StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Videocited by 2
- 2025HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stagecited by 1
- 20253D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Modelcited by 0
- 2025Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Modelscited by 0
- 2026StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video18 May 2026
- 2025Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Models14 Aug 2025
- 2025MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips7 Aug 2025
- 20253D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Model15 Jun 2025
- 2025HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stage3 Mar 2025
- 2024HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models3 Jun 2024
- 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion26 Mar 2024
- 2024Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generation15 Mar 2024
- 2023HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models8 Dec 2023
- 2023Denoising Diffusion for 3D Hand Pose Estimation from Images18 Aug 2023
- 2023DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Models23 May 2023
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
- 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
- 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
- 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
- 2023Reconstructing Hands in 3D with Transformerscited by 298
- 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
- 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 128
- 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
- 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 122
- 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
12 most cited of 226 All 226 (JSON)
- 2026ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild28 Sep 2026
- 2026MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery9 Sep 2026
- 2026Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance Heritage3 Sep 2026
- 2026Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands12 Aug 2026
- 2026DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units4 Aug 2026
- 2026OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting31 Jul 2026
- 2026Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer30 Jul 2026
- 2026Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting17 Jul 2026
- 2026Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction15 Jul 2026
- 2026WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation7 Jul 2026
- 2026Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation1 Jul 2026
- 2026Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation29 Jun 2026
12 newest of 226 All 226 (JSON)