mlsanityData to 14 Oct 2026

Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models

arXiv 2308.02963 ↗First posted 5 Aug 2023cs.CVcited by 14

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

Abstract (arXiv)

This work focuses on the problem of reconstructing a 3D human body mesh from a given 2D image. Despite the inherent ambiguity of the task of human mesh recovery, most existing works have adopted a method of regressing a single output. In contrast, we propose a generative approach framework, called "Diffusion-based Human Mesh Recovery (Diff-HMR)" that takes advantage of the denoising diffusion process to account for multiple plausible outcomes. During the training phase, the SMPL parameters are diffused from ground-truth parameters to random distribution, and Diff-HMR learns the reverse process of this diffusion. In the inference phase, the model progressively refines the given random SMPL parameters into the corresponding parameters that align with the input image. Diff-HMR, being a generative approach, is capable of generating diverse results for the same input image as the input noise varies. We conduct validation experiments, and the results demonstrate that the proposed framework effectively models the inherent ambiguity of the task of human mesh recovery in a probabilistic manner. The code is available at https://github.com/hanbyel0105/Diff-HMR

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 30 of its 40 references that are in the map. First posted on arXiv 5 Aug 2023.

Builds on

30 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan

Other references · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  10. 2017End-to-end Recovery of Human Shape and Posecited by 885
  11. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  12. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
17 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  2. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  3. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  4. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  5. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  6. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  7. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  8. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  9. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  10. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  11. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  12. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  13. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  14. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  15. 2017Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detectionscited by 30
  16. 2021Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learningcited by 17
  17. 2023Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-viewcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recoverycited by 17
  2. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 14
  3. 2025DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Priorcited by 13
  4. 2025ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimizationcited by 7
  5. 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Imagescited by 5
  6. 2024DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Posecited by 3
  7. 2024PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recoverycited by 2
  8. 2025MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstructioncited by 2
  9. 2025PHD: Personalized 3D Human Body Fitting with Point Diffusioncited by 2
  10. 2026DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxiescited by 1
  11. 2025LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusioncited by 0
  12. 2025Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimationcited by 0
2 more
  1. 2026Discriminative-Generative Synergy for Occlusion Robust 3D Human Mesh Recoverycited by 0
  2. 2026MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recoverycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Distribution-Aligned Diffusion for Human Mesh Recovery
  2. 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans
  3. 2023Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domains
  4. 2023DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos
  5. 2024Score-Guided Diffusion for 3D Human Recovery
  6. 2026VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery
  7. 2024DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior
  8. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion