mlsanityData to 14 Oct 2026

Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation

arXiv 2207.07900 ↗First posted 16 Jul 2022cs.CV cs.AI cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

Inter-person occlusion and depth ambiguity make estimating the 3D poses of monocular multiple persons as camera-centric coordinates a challenging problem. Typical top-down frameworks suffer from high computational redundancy with an additional detection stage. By contrast, the bottom-up methods enjoy low computational costs as they are less affected by the number of humans. However, most existing bottom-up methods treat camera-centric 3D human pose estimation as two unrelated subtasks: 2.5D pose estimation and camera-centric depth estimation. In this paper, we propose a unified model that leverages the mutual benefits of both these subtasks. Within the framework, a robust structured 2.5D pose estimation is designed to recognize inter-person occlusion based on depth relationships. Additionally, we develop an end-to-end geometry-aware depth reasoning method that exploits the mutual benefits of both 2.5D pose and camera-centric root depths. This method first uses 2.5D pose and geometry information to infer camera-centric root depths in a forward pass, and then exploits the root depths to further improve representation learning of 2.5D pose estimation in a backward pass. Further, we designed an adaptive fusion scheme that leverages both visual perception and body geometry to alleviate inherent depth ambiguity issues. Extensive experiments demonstrate the superiority of our proposed model over a wide range of bottom-up methods. Our accuracy is even competitive with top-down counterparts. Notably, our model runs much faster than existing bottom-up and top-down methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 58 of its 128 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

58 of 128 references.

References · 58

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Mask R-CNNcited by 7,277
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2019Objects as Pointscited by 1,175
  7. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  8. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  9. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  10. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
38 more
  1. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  2. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  3. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  4. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  5. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  6. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  7. 2017Integral Human Pose Regressioncited by 256
  8. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  9. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  10. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  11. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 181
  12. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  13. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  14. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  15. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  16. 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
  17. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  18. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  19. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  20. 2019Single-Stage Multi-Person Pose Machinescited by 95
  21. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  22. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  23. 2021Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Cameracited by 70
  24. 2019XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Cameracited by 68
  25. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  26. 2017MonoPerfCap: Human Performance Capture from Monocular Videocited by 63
  27. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  28. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  29. 2020Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimationcited by 52
  30. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  31. 2020DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modelingcited by 49
  32. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  33. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  34. 2019Single-Network Whole-Body Pose Estimationcited by 24
  35. 2020Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videoscited by 23
  36. 2021PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimationcited by 22
  37. 2020HDNet: Human Depth Estimation for Multi-Person Camera-Space Localizationcited by 20
  38. 2019Multi-Person 3D Human Pose Estimation from Monocular Imagescited by 19

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.