mlsanityData to 7 Oct 2026

PARE: Part Attention Regressor for 3D Human Body Estimation

arXiv 2104.08527 ↗First posted 17 Apr 2021cs.CVcited by 334

Not on the map. Why?

Abstract (arXiv)

Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address this, we introduce a soft attention mechanism, called the Part Attention REgressor (PARE), that learns to predict body-part-guided attention masks. We observe that state-of-the-art methods rely on global feature representations, making them sensitive to even small occlusions. In contrast, PARE's part-guided attention mechanism overcomes these issues by exploiting information about the visibility of individual body parts while leveraging information from neighboring body-parts to predict occluded parts. We show qualitatively that PARE learns sensible attention masks, and quantitative evaluation confirms that PARE achieves more accurate and robust reconstruction results than existing approaches on both occlusion-specific and standard benchmarks. The code and data are available for research purposes at small urlhttps://pare.is.tue.mpg.de/

Key facts. Cited by 334 papers in the map (data through 7 Oct 2026). Builds on 40 of its 64 references that are in the map. First posted on arXiv 17 Apr 2021.

Builds on

40 of 64 references.

References · 40

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  6. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  7. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2017End-to-end Recovery of Human Shape and Posecited by 883
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  11. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  12. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
28 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  2. 2017Neural 3D Mesh Renderercited by 437
  3. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  4. 2018Learning 3D Human Dynamics from Videocited by 315
  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. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  8. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  9. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  10. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  11. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  12. 2020See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networkscited by 138
  13. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  14. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  15. 2020Epipolar Transformerscited by 117
  16. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  17. 20203D Human Motion Estimation via Motion Compression and Refinementcited by 98
  18. 2017Self-supervised Learning of Motion Capturecited by 97
  19. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  20. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  21. 2020Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wildcited by 82
  22. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  23. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  24. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  25. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  26. 2020Full-Body Awareness from Partial Observationscited by 29
  27. 2018How Robust is 3D Human Pose Estimation to Occlusion?cited by 23
  28. 20203D Pose Detection in Videos: Focusing on Occlusioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 50; 2023: 105; 2024: 84; 2025: 38; 2026: 42.

334 papers.

Sort:

By area:

  1. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  2. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  3. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
  4. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  5. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  6. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  7. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  8. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  9. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  10. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  11. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 154
  12. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
38 more
  1. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  2. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  3. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  4. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  5. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  6. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  7. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  8. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 128
  9. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 127
  10. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  11. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 105
  12. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  13. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  14. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  15. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  16. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  17. 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 93
  18. 2023HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splattingcited by 89
  19. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  20. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  21. 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
  22. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  23. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  24. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  25. 2022Full-Body Articulated Human-Object Interactioncited by 76
  26. 2023ChatPose: Chatting about 3D Human Posecited by 71
  27. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  28. 2023X-Avatar: Expressive Human Avatarscited by 66
  29. 2021Playing for 3D Human Recoverycited by 63
  30. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
  31. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  32. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
  33. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  34. 2022Human-Aware Object Placement for Visual Environment Reconstructioncited by 56
  35. 2024Estimating Body and Hand Motion in an Ego-sensed Worldcited by 56
  36. 2023SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modelingcited by 54
  37. 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
  38. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54

50 most cited of 334 All 334 (JSON)