mlsanityData to 14 Oct 2026

Body Meshes as Points

arXiv 2105.02467 ↗First posted 6 May 2021cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

We consider the challenging multi-person 3D body mesh estimation task in this work. Existing methods are mostly two-stage based--one stage for person localization and the other stage for individual body mesh estimation, leading to redundant pipelines with high computation cost and degraded performance for complex scenes (e.g., occluded person instances). In this work, we present a single-stage model, Body Meshes as Points (BMP), to simplify the pipeline and lift both efficiency and performance. In particular, BMP adopts a new method that represents multiple person instances as points in the spatial-depth space where each point is associated with one body mesh. Hinging on such representations, BMP can directly predict body meshes for multiple persons in a single stage by concurrently localizing person instance points and estimating the corresponding body meshes. To better reason about depth ordering of all the persons within the same scene, BMP designs a simple yet effective inter-instance ordinal depth loss to obtain depth-coherent body mesh estimation. BMP also introduces a novel keypoint-aware augmentation to enhance model robustness to occluded person instances. Comprehensive experiments on benchmarks Panoptic, MuPoTS-3D and 3DPW clearly demonstrate the state-of-the-art efficiency of BMP for multi-person body mesh estimation, together with outstanding accuracy. Code can be found at: https://github.com/jfzhang95/BMP.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 57 of its 76 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

57 of 76 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2018YOLOv3: An Incremental Improvementcited by 2,659
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  8. 2018Group Normalizationcited by 1,524
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  11. 2019Objects as Pointscited by 1,175
  12. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
38 more
  1. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  2. 2017End-to-end Recovery of Human Shape and Posecited by 885
  3. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  4. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  5. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  7. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  10. 2019SOLO: Segmenting Objects by Locationscited by 289
  11. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  12. 2017Integral Human Pose Regressioncited by 256
  13. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  14. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  15. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  16. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  17. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  18. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  19. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  20. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  21. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  22. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  23. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 115
  24. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  25. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  26. 2017Self-supervised Learning of Motion Capturecited by 97
  27. 2019Single-Stage Multi-Person Pose Machinescited by 95
  28. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  29. 2017Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Imagecited by 73
  30. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67
  31. 2020Learning to Transfer Texture from Clothing Images to 3D Humanscited by 58
  32. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  33. 2017Detect-and-Track: Efficient Pose Estimation in Videoscited by 51
  34. 2019Synthetic Humans for Action Recognition from Unseen Viewpointscited by 46
  35. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  36. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  37. 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
  38. 2019FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Secondcited by 35

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 10; 2024: 11; 2025: 3; 2026: 3.

45 papers.

Sort:

By area:

  1. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  2. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 153
  3. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  4. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  5. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 142
  6. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 139
  7. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  8. 20233D Human Pose Estimation via Intuitive Physicscited by 103
  9. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  10. 2022Occluded Human Mesh Recoverycited by 54
  11. 2024HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environmentcited by 53
  12. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 48
33 more
  1. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 34
  2. 2023Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Viewscited by 33
  3. 2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
  4. 2021HSPACE: Synthetic Parametric Humans Animated in Complex Environmentscited by 29
  5. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  6. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
  7. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 19
  8. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  9. 2024COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimationcited by 15
  10. 2023Rendering Humans from Object-Occluded Monocular Videoscited by 14
  11. 2023Crowd3D: Towards Hundreds of People Reconstruction from a Single Imagecited by 12
  12. 2021Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Imagescited by 11
  13. 2022Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinementcited by 11
  14. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  15. 2023IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiationcited by 9
  16. 2024STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusioncited by 9
  17. 2023Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videoscited by 5
  18. 2021View Birdification in the Crowd: Ground-Plane Localization from Perceived Movementscited by 4
  19. 20243D Reconstruction of Interacting Multi-Person in Clothing from a Single Imagecited by 4
  20. 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoningcited by 4
  21. 2022Permutation-Invariant Relational Network for Multi-person 3D Pose Estimationcited by 3
  22. 2022MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Posecited by 3
  23. 2025DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Videocited by 3
  24. 2025Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Spacecited by 3
  25. 2024Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Imagescited by 2
  26. 2024RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Imagecited by 2
  27. 2023InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Viewscited by 1
  28. 2026Masked Modeling for Human Motion Recovery Under Occlusionscited by 1
  29. 2024Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Lossescited by 0
  30. 2024Human Shape and Clothing Estimationcited by 0
  31. 2024Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignmentcited by 0
  32. 2026InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recoverycited by 0
  33. 2026Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recoverycited by 0