mlsanityData to 14 Oct 2026

VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image

arXiv 2504.14618 ↗First posted 20 Apr 2025cs.CV cs.AIcited by 2

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

Understanding bimanual hand interactions is essential for realistic 3D pose and shape reconstruction. However, existing methods struggle with occlusions, ambiguous appearances, and computational inefficiencies. To address these challenges, we propose Vision Mamba Bimanual Hand Interaction Network (VM-BHINet), introducing state space models (SSMs) into hand reconstruction to enhance interaction modeling while improving computational efficiency. The core component, Vision Mamba Interaction Feature Extraction Block (VM-IFEBlock), combines SSMs with local and global feature operations, enabling deep understanding of hand interactions. Experiments on the InterHand2.6M dataset show that VM-BHINet reduces Mean per-joint position error (MPJPE) and Mean per-vertex position error (MPVPE) by 2-3%, significantly surpassing state-of-the-art methods.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 29 of its 53 references that are in the map. First posted on arXiv 20 Apr 2025.

Builds on

29 of 53 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  5. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  6. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  7. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  8. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 123
  9. 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
  10. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  11. 2021Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Cameracited by 70
  12. 2020NeuralAnnot: Neural Annotator for 3D Human Mesh Training Setscited by 62
17 more
  1. 2019Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interactioncited by 48
  2. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  3. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  4. 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
  5. 2020Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamicscited by 34
  6. 2020Two-hand Global 3D Pose Estimation Using Monocular RGBcited by 27
  7. 2021Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinementscited by 27
  8. 2021RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Videocited by 23
  9. 2021HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeletoncited by 16
  10. 2023A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 15
  11. 2022Multi-modal Fusion Technology based on Vehicle Information: A Surveycited by 13
  12. 2025MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perceptioncited by 10
  13. 2023MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstructioncited by 8
  14. 2023Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recoverycited by 7
  15. 2022LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstructioncited by 5
  16. 2023Path Planning for Air-Ground Robot Considering Modal Switching Point Optimizationcited by 5
  17. 2024MIPD: A Multi-sensory Interactive Perception Dataset for Embodied Intelligent Drivingcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025TEM^3-Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive Drivingcited by 3
  2. 2025CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions
  2. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
  3. 2026HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation
  4. 2024HandS3C: 3D Hand Mesh Reconstruction with State Space Spatial Channel Attention from RGB images
  5. 2025BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
  6. 2026Fast-HaMeR: Boosting Hand Mesh Reconstruction using Knowledge Distillation
  7. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions
  8. 2023ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation