mlsanityData to 14 Oct 2026

FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models

arXiv 2405.05216 ↗First posted 8 May 2024cs.CVcited by 23

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

Abstract (arXiv)

The 3D Human Pose Estimation (3D HPE) task uses 2D images or videos to predict human joint coordinates in 3D space. Despite recent advancements in deep learning-based methods, they mostly ignore the capability of coupling accessible texts and naturally feasible knowledge of humans, missing out on valuable implicit supervision to guide the 3D HPE task. Moreover, previous efforts often study this task from the perspective of the whole human body, neglecting fine-grained guidance hidden in different body parts. To this end, we present a new Fine-Grained Prompt-Driven Denoiser based on a diffusion model for 3D HPE, named FinePOSE. It consists of three core blocks enhancing the reverse process of the diffusion model: (1) Fine-grained Part-aware Prompt learning (FPP) block constructs fine-grained part-aware prompts via coupling accessible texts and naturally feasible knowledge of body parts with learnable prompts to model implicit guidance. (2) Fine-grained Prompt-pose Communication (FPC) block establishes fine-grained communications between learned part-aware prompts and poses to improve the denoising quality. (3) Prompt-driven Timestamp Stylization (PTS) block integrates learned prompt embedding and temporal information related to the noise level to enable adaptive adjustment at each denoising step. Extensive experiments on public single-human pose estimation datasets show that FinePOSE outperforms state-of-the-art methods. We further extend FinePOSE to multi-human pose estimation. Achieving 34.3mm average MPJPE on the EgoHumans dataset demonstrates the potential of FinePOSE to deal with complex multi-human scenarios. Code is available at https://github.com/PKU-ICST-MIPL/FinePOSECVPR2024.

Key facts. Cited by 23 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 52 of its 59 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

52 of 59 references.

References · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  8. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  9. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
38 more
  1. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  2. 2021GPT Understands, Toocited by 716
  3. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  4. 2022Blended Latent Diffusioncited by 432
  5. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  6. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  7. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  8. 2022Prompt Distribution Learningcited by 235
  9. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  10. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 187
  11. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  12. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  13. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  14. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  15. 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
  16. 2022FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessmentcited by 107
  17. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  18. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  19. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  20. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  21. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 92
  22. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  23. 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
  24. 2019Oops! Predicting Unintentional Action in Videocited by 82
  25. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  26. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  27. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  28. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  29. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  30. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  31. 2021Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Drivingcited by 40
  32. 2022Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encodingcited by 39
  33. 2020GraphMDN: Leveraging graph structure and deep learning to solve inverse problemscited by 26
  34. 2023SportsPose -- A Dynamic 3D sports pose datasetcited by 26
  35. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  36. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  37. 2018Soccer on Your Tabletopcited by 20
  38. 2021Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimationcited by 18

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 17; 2026: 4.

23 papers.

Sort:

By area:

  1. 2025Towards Balanced Multi-Modal Learning in 3D Human Pose Estimationcited by 12
  2. 2025Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinatescited by 12
  3. 2024TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Mapscited by 11
  4. 2025HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomalycited by 4
  5. 2025Benchmarking 3D Human Pose Estimation Models under Occlusionscited by 3
  6. 2025Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learningcited by 3
  7. 2024BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustmentcited by 2
  8. 2025NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimationcited by 2
  9. 2025PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networkscited by 2
  10. 2025DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimationcited by 2
  11. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimationcited by 2
  12. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
11 more
  1. 2025Quality assessment of 3D human animation: Subjective and objective evaluationcited by 1
  2. 2025StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusioncited by 1
  3. 2025Gait Recognition via Collaborating Discriminative and Generative Diffusion Modelscited by 1
  4. 2025Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretrainingcited by 0
  5. 2025HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimationcited by 0
  6. 2025KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Videocited by 0
  7. 2025HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimationcited by 0
  8. 2025Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruningcited by 0
  9. 2026Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinatescited by 0
  10. 2026HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimationcited by 0
  11. 2026Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling
  2. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
  3. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  4. 2025DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
  5. 2024PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
  6. 2024D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement
  7. 2022A generic diffusion-based approach for 3D human pose prediction in the wild
  8. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation