mlsanityData to 14 Oct 2026

ReFit: Recurrent Fitting Network for 3D Human Recovery

arXiv 2308.11184 ↗First posted 22 Aug 2023cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

We present Recurrent Fitting (ReFit), a neural network architecture for single-image, parametric 3D human reconstruction. ReFit learns a feedback-update loop that mirrors the strategy of solving an inverse problem through optimization. At each iterative step, it reprojects keypoints from the human model to feature maps to query feedback, and uses a recurrent-based updater to adjust the model to fit the image better. Because ReFit encodes strong knowledge of the inverse problem, it is faster to train than previous regression models. At the same time, ReFit improves state-of-the-art performance on standard benchmarks. Moreover, ReFit applies to other optimization settings, such as multi-view fitting and single-view shape fitting. Project website: https://yufu-wang.github.io/refit_humans/

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Builds on 54 of its 74 references that are in the map. First posted on arXiv 22 Aug 2023.

Builds on

54 of 74 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  9. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  10. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  11. 2017End-to-end Recovery of Human Shape and Posecited by 885
  12. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
38 more
  1. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  2. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  3. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  4. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  5. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  6. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  7. 2018Learning 3D Human Dynamics from Videocited by 316
  8. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  9. 2021Mesh Graphormercited by 265
  10. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  11. 2017Learned Primal-dual Reconstructioncited by 251
  12. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  13. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  14. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  15. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  16. 2014Efficient Object Localization Using Convolutional Networkscited by 227
  17. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  18. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  19. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  20. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  21. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  22. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  23. 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
  24. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  25. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  26. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  27. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  28. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  29. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  30. 2021On Self-Contact and Human Posecited by 89
  31. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  32. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  33. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  34. 2020Neural Descent for Visual 3D Human Pose and Shapecited by 60
  35. 2020Human Mesh Recovery from Multiple Shotscited by 52
  36. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  37. 2020Beyond Weak Perspective for Monocular 3D Human Pose Estimationcited by 29
  38. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 17; 2025: 15; 2026: 11.

47 papers.

Sort:

By area:

  1. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 206
  2. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 137
  3. 2023GART: Gaussian Articulated Template Modelscited by 121
  4. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 106
  5. 2025PromptHMR: Promptable Human Mesh Recoverycited by 76
  6. 2024CameraHMR: Aligning People with Perspectivecited by 65
  7. 2025GENMO: A GENeralist Model for Human MOtioncited by 49
  8. 2024Score-Guided Diffusion for 3D Human Recoverycited by 39
  9. 2024iHuman: Instant Animatable Digital Humans From Monocular Videoscited by 17
  10. 2025CoMotion: Concurrent Multi-person 3D Motioncited by 13
  11. 2024PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environmentscited by 11
  12. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
35 more
  1. 2026UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Passcited by 9
  2. 2024MeshPose: Unifying DensePose and 3D Body Mesh reconstructioncited by 8
  3. 2025HoliGS: Holistic Gaussian Splatting for Embodied View Synthesiscited by 7
  4. 2024Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videoscited by 6
  5. 2025DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recoverycited by 6
  6. 2026THFM: A Unified Video Foundation Model for 4D Human Perception and Beyondcited by 5
  7. 2024EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimationcited by 4
  8. 2024Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recoverycited by 4
  9. 2025PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generationcited by 4
  10. 2025MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Imagescited by 4
  11. 2026OnlineHMR: Video-based Online World-Grounded Human Mesh Recoverycited by 4
  12. 2023W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibrationcited by 3
  13. 2025PI-HMR: Towards Robust In-bed Temporal Human Shape Reconstruction with Contact Pressure Sensingcited by 3
  14. 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capturecited by 3
  15. 2024Multi-Human Mesh Recovery with Transformerscited by 2
  16. 2025Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematicscited by 2
  17. 2025PHD: Personalized 3D Human Body Fitting with Point Diffusioncited by 2
  18. 2025SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recoverycited by 2
  19. 2026GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstructioncited by 2
  20. 2024Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recoverycited by 1
  21. 2024A vision-based framework for human behavior understanding in industrial assembly linescited by 1
  22. 2024Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Modelscited by 1
  23. 2024D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimationcited by 1
  24. 2025Learning Efficient and Generalizable Human Representation with Human Gaussian Modelcited by 1
  25. 2026MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglementcited by 1
  26. 2026UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Videocited by 1
  27. 2026Anny-Fit: All-Age Human Mesh Recoverycited by 1
  28. 2026EgoExoMoCap: Distributed Ego-Exo Human Motion Capturecited by 1
  29. 2023Temporal-Aware Refinement for Video-based Human Pose and Shape Recoverycited by 0
  30. 2024Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Lossescited by 0
  31. 2025ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimationcited by 0
  32. 2025WATCH: World-aware Allied Trajectory and pose reConstruction for Camera and Humancited by 0
  33. 2025From Camera to World: A Plug-and-Play Module for Human Mesh Transformationcited by 0
  34. 2026Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capturecited by 0
  35. 2026Meta-Learned Adaptive Optimization for Robust Human Mesh Recovery with Uncertainty-Aware Parameter Updatescited by 0