mlsanityData to 14 Oct 2026

MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image

arXiv 2112.02753 ↗First posted 6 Dec 2021cs.CVcited by 74

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence. Specifically, for 2D encoding, we propose lightweight yet effective stacked structures. Regarding 3D decoding, we provide an efficient graph operator, namely depth-separable spiral convolution. Moreover, we present a novel feature lifting module for bridging the gap between 2D and 3D representations. This module begins with a map-based position regression (MapReg) block to integrate the merits of both heatmap encoding and position regression paradigms for improved 2D accuracy and temporal coherence. Furthermore, MapReg is followed by pose pooling and pose-to-vertex lifting approaches, which transform 2D pose encodings to semantic features of 3D vertices. Overall, our hand reconstruction framework, called MobRecon, comprises affordable computational costs and miniature model size, which reaches a high inference speed of 83FPS on Apple A14 CPU. Extensive experiments on popular datasets such as FreiHAND, RHD, and HO3Dv2 demonstrate that our MobRecon achieves superior performance on reconstruction accuracy and temporal coherence. Our code is publicly available at https://github.com/SeanChenxy/HandMesh.

Key facts. Cited by 74 papers in the map (data through 14 Oct 2026). Builds on 73 of its 98 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

73 of 98 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  9. 2019Searching for MobileNetV3cited by 1,994
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  12. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
38 more
  1. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  2. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  4. 2019GhostNet: More Features from Cheap Operationscited by 410
  5. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  6. 2016Convolutional Pose Machinescited by 325
  7. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  8. 2018Learning 3D Human Dynamics from Videocited by 316
  9. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  10. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  11. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  12. 2021Mesh Graphormercited by 265
  13. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  14. 2017Integral Human Pose Regressioncited by 256
  15. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  16. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  17. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  18. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  19. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
  20. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  21. 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 179
  22. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  23. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  24. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
  25. 2019NASA: Neural Articulated Shape Approximationcited by 149
  26. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  27. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  28. 2020Reconstructing Hand-Object Interactions in the Wildcited by 144
  29. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 141
  30. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  31. 2020CPF: Learning a Contact Potential Field to Model the Hand-Object Interactioncited by 128
  32. 2017Compositional Human Pose Regressioncited by 124
  33. 2019End-to-end Hand Mesh Recovery from a Monocular RGB Imagecited by 124
  34. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  35. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  36. 2018Hand Pose Estimation via Latent 2.5D Heatmap Regressioncited by 111
  37. 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
  38. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 16; 2024: 24; 2025: 19; 2026: 12.

74 papers.

Sort:

By area:

  1. 2023Reconstructing Hands in 3D with Transformerscited by 306
  2. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 162
  3. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 124
  4. 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 88
  5. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  6. 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
  7. 2023A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Imagecited by 32
  8. 2024A Simple Baseline for Efficient Hand Mesh Reconstructioncited by 27
  9. 2022DART: Articulated Hand Model with Diverse Accessories and Rich Texturescited by 25
  10. 2023Mobile Foundation Model as Firmwarecited by 25
  11. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  12. 2025Predicting 4D Hand Trajectory from Monocular Videoscited by 21
38 more
  1. 2023High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decompositioncited by 18
  2. 2023EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervisioncited by 17
  3. 2024HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fieldscited by 14
  4. 2024Complementing Event Streams and RGB Frames for Hand Mesh Reconstructioncited by 14
  5. 2024HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Modelscited by 14
  6. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactionscited by 13
  7. 2022MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstructioncited by 11
  8. 2024PEAR: Phrase-Based Hand-Object Interaction Anticipationcited by 10
  9. 2024RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidancecited by 9
  10. 2024HandOS: 3D Hand Reconstruction in One Stagecited by 9
  11. 2023Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Imagecited by 8
  12. 2023HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learningcited by 7
  13. 2023DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Modelscited by 7
  14. 2024HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioningcited by 7
  15. 2025EDM: Efficient Deep Feature Matchingcited by 7
  16. 2023Neural Voting Field for Camera-Space 3D Hand Pose Estimationcited by 6
  17. 2024Multi-view Hand Reconstruction with a Point-Embedded Transformercited by 6
  18. 2025UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimationcited by 6
  19. 2023CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Promptingcited by 5
  20. 2024Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidancecited by 5
  21. 2024MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wildcited by 5
  22. 2025Diffusion-based 3D Hand Motion Recovery with Intuitive Physicscited by 5
  23. 2023Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstructioncited by 4
  24. 2024HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Imagescited by 4
  25. 2025Hand-Shadow Posercited by 4
  26. 2026PAD-Hand: Physics-Aware Diffusion for Hand Motion Recoverycited by 4
  27. 20231st Place Solution of Egocentric 3D Hand Pose Estimation Challenge 2023 Technical Report:A Concise Pipeline for Egocentric Hand Pose Reconstructioncited by 3
  28. 2024Low-Energy On-Device Personalization for MCUscited by 3
  29. 2024MLPHand: Real Time Multi-View 3D Hand Mesh Reconstruction via MLP Modelingcited by 3
  30. 2025QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objectscited by 3
  31. 2025Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoderscited by 3
  32. 2026EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learningcited by 3
  33. 2026PEAR: Pixel-aligned Expressive humAn mesh Recoverycited by 3
  34. 2026EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Cameracited by 3
  35. 2024SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptationcited by 2
  36. 20243D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenariocited by 2
  37. 2024XHand: Real-time Expressive Hand Avatarcited by 2
  38. 2025Rodrigues Network for Learning Robot Actionscited by 2

50 most cited of 74 All 74 (JSON)