mlsanityData to 14 Oct 2026

LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction

arXiv 2208.09815 ↗First posted 21 Aug 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed great success for hand reconstruction in real-time applications such as visual reality and augmented reality while interacting with two-hand reconstruction through efficient transformers is left unexplored. In this paper, we propose a method called lightweight attention hand (LWA-HAND) to reconstruct hands in low flops from a single RGB image. To solve the occlusion and interaction problem in efficient attention architectures, we propose three mobile attention modules in this paper. The first module is a lightweight feature attention module that extracts both local occlusion representation and global image patch representation in a coarse-to-fine manner. The second module is a cross image and graph bridge module which fuses image context and hand vertex. The third module is a lightweight cross-attention mechanism that uses element-wise operation for the cross-attention of two hands in linear complexity. The resulting model achieves comparable performance on the InterHand2.6M benchmark in comparison with the state-of-the-art models. Simultaneously, it reduces the flops to 0.47GFlops while the state-of-the-art models have heavy computations between 10GFlops and 20GFlops.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 44 of its 55 references that are in the map. First posted on arXiv 21 Aug 2022.

Builds on

44 of 55 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2019Searching for MobileNetV3cited by 1,994
  8. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  9. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  12. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
32 more
  1. 2021Mesh Graphormercited by 265
  2. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  3. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  4. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  5. 2021Mobile-Former: Bridging MobileNet and Transformercited by 235
  6. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  7. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  8. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  9. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 181
  10. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  11. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  12. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  13. 2020MediaPipe Hands: On-device Real-time Hand Trackingcited by 161
  14. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  15. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  16. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  17. 2019End-to-end Hand Mesh Recovery from a Monocular RGB Imagecited by 124
  18. 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
  19. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  20. 2020Monocular Real-time Hand Shape and Motion Capture using Multi-modal Datacited by 106
  21. 2018Cross-modal Deep Variational Hand Pose Estimationcited by 89
  22. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  23. 2020FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integrationcited by 73
  24. 2021Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Cameracited by 70
  25. 2021Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registrationcited by 59
  26. 2020Monocular Real-time Full Body Capture with Inter-part Correlationscited by 53
  27. 2021Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstructioncited by 44
  28. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  29. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 33
  30. 2021Hand Image Understanding via Deep Multi-Task Learningcited by 31
  31. 2021Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinementscited by 27
  32. 2021RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Videocited by 23

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 0; 2025: 1.

5 papers.

  1. 2023Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wildcited by 36
  2. 2023A Dataset of Relighted 3D Interacting Handscited by 35
  3. 2023HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Modelscited by 13
  4. 2023Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recoverycited by 7
  5. 2025VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Imagecited by 2