mlsanityData to 7 Oct 2026

Reconstructing 3D Human Pose by Watching Humans in the Mirror

arXiv 2104.00340 ↗First posted 1 Apr 2021cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce the new task of reconstructing 3D human pose from a single image in which we can see the person and the person's image through a mirror. Compared to general scenarios of 3D pose estimation from a single view, the mirror reflection provides an additional view for resolving the depth ambiguity. We develop an optimization-based approach that exploits mirror symmetry constraints for accurate 3D pose reconstruction. We also provide a method to estimate the surface normal of the mirror from vanishing points in the single image. To validate the proposed approach, we collect a large-scale dataset named Mirrored-Human, which covers a large variety of human subjects, poses and backgrounds. The experiments demonstrate that, when trained on Mirrored-Human with our reconstructed 3D poses as pseudo ground-truth, the accuracy and generalizability of existing single-view 3D pose estimators can be largely improved.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 42 of its 69 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

42 of 69 references.

References · 42

  1. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  4. 2017End-to-end Recovery of Human Shape and Posecited by 883
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  11. 2018Learning 3D Human Dynamics from Videocited by 315
  12. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
30 more
  1. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  2. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  3. 2017Integral Human Pose Regressioncited by 255
  4. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  5. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  6. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  7. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  8. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  9. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  10. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  11. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  12. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  13. 2017Compositional Human Pose Regressioncited by 124
  14. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  15. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 112
  16. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  17. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  18. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  19. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  20. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  21. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  22. 2018Learning to Detect and Track Visible and Occluded Body Joints in a Virtual Worldcited by 81
  23. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  24. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  25. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  26. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  27. 2020Motion Capture from Internet Videoscited by 33
  28. 2021PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimationcited by 22
  29. 2020HDNet: Human Depth Estimation for Multi-Person Camera-Space Localizationcited by 20
  30. 2019Multi-Person 3D Human Pose Estimation from Monocular Imagescited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 9; 2023: 16; 2024: 9; 2025: 2; 2026: 7.

47 papers.

Sort:

  1. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  2. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  3. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  4. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  7. 2022PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequencecited by 46
  8. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 46
  9. 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
  10. 2023Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstructioncited by 41
  11. 2023Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Viewscited by 33
  12. 2023HAP: Structure-Aware Masked Image Modeling for Human-Centric Perceptioncited by 33
35 more
  1. 2023Relightable and Animatable Neural Avatar from Sparse-View Videocited by 28
  2. 2023NPC: Neural Point Characters from Videocited by 26
  3. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  4. 2023Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modelingcited by 19
  5. 2022PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimationcited by 18
  6. 2023FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Viewscited by 15
  7. 2024Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videocited by 12
  8. 2021Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Imagescited by 11
  9. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
  10. 2022DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimationcited by 8
  11. 2023MoRF: Mobile Realistic Fullbody Avatars from a Monocular Videocited by 7
  12. 2023Learning Dense UV Completion for Human Mesh Recoverycited by 7
  13. 2023FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditionscited by 7
  14. 2023A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimizationcited by 5
  15. 2024Structure from Duplicates: Neural Inverse Graphics from a Pile of Objectscited by 5
  16. 2024TalkinNeRF: Animatable Neural Fields for Full-Body Talking Humanscited by 4
  17. 2024WildAvatar: Learning In-the-wild 3D Avatars from the Webcited by 3
  18. 2023Multimodal Active Measurement for Human Mesh Recovery in Close Proximitycited by 2
  19. 2023Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performancescited by 2
  20. 2024TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scenecited by 2
  21. 2025Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflectionscited by 2
  22. 2022Decanus to Legatus: Synthetic training for 2D-3D human pose liftingcited by 1
  23. 2024Active Human Pose Estimation via an Autonomous UAV Agentcited by 1
  24. 2026PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptationcited by 1
  25. 2026PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitationcited by 1
  26. 2026HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Videocited by 1
  27. 2023Mirror-Aware Neural Humanscited by 0
  28. 20233DHR-Co: A Collaborative Test-time Refinement Framework for In-the-Wild 3D Human-Body Reconstruction Taskcited by 0
  29. 2023MirrorCalib: Utilizing Human Pose Information for Mirror-based Virtual Camera Calibrationcited by 0
  30. 2024Fusion of Short-term and Long-term Attention for Video Mirror Detectioncited by 0
  31. 2025MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentationcited by 0
  32. 2026Masked Modeling for Human Motion Recovery Under Occlusionscited by 0
  33. 2026Does it matter which Gaussians you pick in 4D Gaussian streaming?cited by 0
  34. 2026Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervisioncited by 0
  35. 2026Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learningcited by 0