mlsanityData to 14 Oct 2026

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

arXiv 2208.00571 ↗First posted 1 Aug 2022cs.CVcited by 238

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem. However, cropping, their first step, discards the location information from the very beginning, which makes themselves unable to accurately predict the global rotation in the original camera coordinate system. To address this problem, we propose to Carry Location Information in Full Frames (CLIFF) into this task. Specifically, we feed more holistic features to CLIFF by concatenating the cropped-image feature with its bounding box information. We calculate the 2D reprojection loss with a broader view of the full frame, taking a projection process similar to that of the person projected in the image. Fed and supervised by global-location-aware information, CLIFF directly predicts the global rotation along with more accurate articulated poses. Besides, we propose a pseudo-ground-truth annotator based on CLIFF, which provides high-quality 3D annotations for in-the-wild 2D datasets and offers crucial full supervision for regression-based methods. Extensive experiments on popular benchmarks show that CLIFF outperforms prior arts by a significant margin, and reaches the first place on the AGORA leaderboard (the SMPL-Algorithms track). The code and data are available at https://github.com/huawei-noah/noah-research/tree/master/CLIFF.

Key facts. Cited by 238 papers in the map (data through 14 Oct 2026). Builds on 50 of its 63 references that are in the map. First posted on arXiv 1 Aug 2022.

Builds on

50 of 63 references.

References · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2018YOLOv3: An Incremental Improvementcited by 2,659
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  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. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  5. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  6. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  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. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  10. 2021Mesh Graphormercited by 265
  11. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  12. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  13. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  14. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  15. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  16. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  17. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  18. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  19. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  20. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  21. 2021On Self-Contact and Human Posecited by 89
  22. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  23. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  24. 2020Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wildcited by 82
  25. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  26. 2021Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimationcited by 62
  27. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 50
  28. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  29. 2021Body Meshes as Pointscited by 45
  30. 2021Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstructioncited by 39
  31. 2019Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wildcited by 38
  32. 2021Adversarial Parametric Pose Priorcited by 38
  33. 2020Full-Body Awareness from Partial Observationscited by 29
  34. 2020Beyond Weak Perspective for Monocular 3D Human Pose Estimationcited by 29
  35. 2021Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptationcited by 24
  36. 2018How Robust is 3D Human Pose Estimation to Occlusion?cited by 23
  37. 2020PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layerscited by 16
  38. 2022AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 60; 2024: 70; 2025: 54; 2026: 48.

238 papers.

Sort:

By area:

  1. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  2. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  3. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 206
  4. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  5. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 155
  6. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 142
  7. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 137
  8. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 106
  9. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  10. 20233D Human Pose Estimation via Intuitive Physicscited by 103
  11. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 101
  12. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 97
38 more
  1. 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 95
  2. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 91
  3. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  4. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  5. 2025PromptHMR: Promptable Human Mesh Recoverycited by 76
  6. 2023ChatPose: Chatting about 3D Human Posecited by 72
  7. 2026SAM 3D Body: Robust Full-Body Human Mesh Recoverycited by 69
  8. 2024CameraHMR: Aligning People with Perspectivecited by 65
  9. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  10. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 59
  11. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  12. 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
  13. 2024HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environmentcited by 53
  14. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 49
  15. 2025GENMO: A GENeralist Model for Human MOtioncited by 49
  16. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 48
  17. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  18. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  19. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  20. 2023Digital Life Project: Autonomous 3D Characters with Social Intelligencecited by 43
  21. 2024AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimationcited by 42
  22. 2023Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstructioncited by 41
  23. 2024Score-Guided Diffusion for 3D Human Recoverycited by 39
  24. 2022One-shot Implicit Animatable Avatars with Model-based Priorscited by 38
  25. 2023Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generationcited by 38
  26. 2025Human3R: Everyone Everywhere All at Oncecited by 37
  27. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 34
  28. 2023Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Viewscited by 33
  29. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 32
  30. 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactionscited by 31
  31. 2024Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformercited by 29
  32. 2024Towards Open Domain Text-Driven Synthesis of Multi-Person Motionscited by 29
  33. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  34. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 28
  35. 2024EgoGen: An Egocentric Synthetic Data Generatorcited by 27
  36. 2023Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Videocited by 25
  37. 2023Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimationcited by 24
  38. 2024Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRMcited by 23

50 most cited of 238 All 238 (JSON)