mlsanityData to 7 Oct 2026

Score-Guided Diffusion for 3D Human Recovery

arXiv 2403.09623 ↗First posted 14 Mar 2024cs.CVcited by 39

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction. These inverse problems involve fitting a human body model to image observations, traditionally solved through optimization techniques. ScoreHMR mimics model fitting approaches, but alignment with the image observation is achieved through score guidance in the latent space of a diffusion model. The diffusion model is trained to capture the conditional distribution of the human model parameters given an input image. By guiding its denoising process with a task-specific score, ScoreHMR effectively solves inverse problems for various applications without the need for retraining the task-agnostic diffusion model. We evaluate our approach on three settings/applications. These are: (i) single-frame model fitting; (ii) reconstruction from multiple uncalibrated views; (iii) reconstructing humans in video sequences. ScoreHMR consistently outperforms all optimization baselines on popular benchmarks across all settings. We make our code and models available at the https://statho.github.io/ScoreHMR.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 58 of its 71 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

58 of 71 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023AVID: Any-Length Video Inpainting with Diffusion Model6 Dec

Other references · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  11. 2016Layer Normalizationcited by 5,579
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
38 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  6. 2022Human Motion Diffusion Modelcited by 1,062
  7. 2017End-to-end Recovery of Human Shape and Posecited by 883
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  9. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  10. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  11. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  13. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  14. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  15. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  16. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  17. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  18. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  19. 2018Learning 3D Human Dynamics from Videocited by 315
  20. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  21. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  22. 2021Mesh Graphormercited by 264
  23. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  24. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  25. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  26. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  27. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  28. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  29. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  30. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  31. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  32. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  33. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  34. 2023Improving Tuning-Free Real Image Editing with Proximal Guidancecited by 87
  35. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  36. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  37. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  38. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 19; 2026: 13.

39 papers.

Sort:

By area:

  1. 2025REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioningcited by 14
  2. 2025Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinatescited by 12
  3. 2024Diffusion Models in 3D Vision: A Surveycited by 11
  4. 2025ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusioncited by 9
  5. 2025ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videoscited by 8
  6. 2025DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recoverycited by 6
  7. 2025ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimizationcited by 6
  8. 2026DuoMo: Dual Motion Diffusion for World-Space Human Reconstructioncited by 6
  9. 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Imagescited by 5
  10. 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoningcited by 4
  11. 2025FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decodingcited by 4
  12. 2024Exploring the Potential of Synthetic Data to Replace Real Datacited by 3
27 more
  1. 2025Dance Style Recognition Using Laban Movement Analysiscited by 3
  2. 2025AJAHR: Amputated Joint Aware 3D Human Mesh Recoverycited by 3
  3. 2026FMPose3D: monocular 3D pose estimation via flow matchingcited by 3
  4. 2024DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Modelscited by 2
  5. 2024Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Priorcited by 2
  6. 2024HeatFormer: A Neural Optimizer for Multiview Human Mesh Recoverycited by 2
  7. 2025CASIM: Composite Aware Semantic Injection for Text to Motion Generationcited by 2
  8. 2025SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Modelscited by 2
  9. 2025PHD: Personalized 3D Human Body Fitting with Point Diffusioncited by 2
  10. 2025Affordance-Guided Diffusion Prior for 3D Hand Reconstructioncited by 2
  11. 2026VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recoverycited by 2
  12. 2024SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perceptioncited by 1
  13. 2026DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxiescited by 1
  14. 2026PEAR: Pixel-aligned Expressive humAn mesh Recoverycited by 1
  15. 2025AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generationcited by 0
  16. 2025SHaDe: Compact and Consistent Dynamic 3D Reconstruction via Tri-Plane Deformation and Latent Diffusioncited by 0
  17. 2025LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusioncited by 0
  18. 2025Zero-shot Human Pose Estimation using Diffusion-based Inverse solverscited by 0
  19. 2025On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimationcited by 0
  20. 2026Towards Geometry-Aware and Motion-Guided Video Human Mesh Recoverycited by 0
  21. 2026Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinatescited by 0
  22. 2026Monocular Models are Strong Learners for Multi-View Human Mesh Recoverycited by 0
  23. 2026Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recoverycited by 0
  24. 2026FactorizedHMR: A Hybrid Framework for Video Human Mesh Recoverycited by 0
  25. 2026ARAPDiffusion: ARAP Regularization for Diffusion-Based Deformable Shape Space Learningcited by 0
  26. 2026RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animationcited by 0
  27. 2026Generalist Open-World Temporal Perceptioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models
  2. 2023DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos
  3. 2023Distribution-Aligned Diffusion for Human Mesh Recovery
  4. 2026OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
  5. 2024DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
  6. 2025MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images
  7. 2023DPoser: Diffusion Model as Robust 3D Human Pose Prior
  8. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion