mlsanityData to 7 Oct 2026

Human Mesh Recovery from Arbitrary Multi-view Images

arXiv 2403.12434 ↗First posted 19 Mar 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Human mesh recovery from arbitrary multi-view images involves two characteristics: the arbitrary camera poses and arbitrary number of camera views. Because of the variability, designing a unified framework to tackle this task is challenging. The challenges can be summarized as the dilemma of being able to simultaneously estimate arbitrary camera poses and recover human mesh from arbitrary multi-view images while maintaining flexibility. To solve this dilemma, we propose a divide and conquer framework for Unified Human Mesh Recovery (U-HMR) from arbitrary multi-view images. In particular, U-HMR consists of a decoupled structure and two main components: camera and body decoupling (CBD), camera pose estimation (CPE), and arbitrary view fusion (AVF). As camera poses and human body mesh are independent of each other, CBD splits the estimation of them into two sub-tasks for two individual sub-networks (ie, CPE and AVF) to handle respectively, thus the two sub-tasks are disentangled. In CPE, since each camera pose is unrelated to the others, we adopt a shared MLP to process all views in a parallel way. In AVF, in order to fuse multi-view information and make the fusion operation independent of the number of views, we introduce a transformer decoder with a SMPL parameters query token to extract cross-view features for mesh recovery. To demonstrate the efficacy and flexibility of the proposed framework and effect of each component, we conduct extensive experiments on three public datasets: Human3.6M, MPI-INF-3DHP, and TotalCapture.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 54 of its 71 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

54 of 71 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  7. 2017End-to-end Recovery of Human Shape and Posecited by 883
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  9. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  10. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  11. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  12. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
38 more
  1. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  2. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  3. 2016Convolutional Pose Machinescited by 325
  4. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  5. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  6. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  7. 2021Mesh Graphormercited by 264
  8. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  9. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  10. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  11. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  12. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  13. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  14. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  15. 2019Learnable Triangulation of Human Posecited by 160
  16. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  17. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  18. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  19. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 128
  20. 2020Epipolar Transformerscited by 117
  21. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  22. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  23. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  24. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  25. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  26. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  27. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  28. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  29. 2022TORE: Token Reduction for Efficient Human Mesh Recovery with Transformercited by 41
  30. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  31. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  32. 2019Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Imagescited by 28
  33. 2020Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approachcited by 27
  34. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  35. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  36. 2022PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimationcited by 18
  37. 2022Learnable human mesh triangulation for 3D human pose and shape estimationcited by 16
  38. 2018Deep Autoencoder for Combined Human Pose Estimation and body Model Upscalingcited by 12

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 4.

5 papers.

  1. 2024HeatFormer: A Neural Optimizer for Multiview Human Mesh Recoverycited by 2
  2. 2026DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxiescited by 1
  3. 2026AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priorscited by 1
  4. 2026Monocular Models are Strong Learners for Multi-View Human Mesh Recoverycited by 0
  5. 2026ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Enginecited by 0