mlsanityData to 7 Oct 2026

Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models

arXiv 2301.03949 ↗First posted 10 Jan 2023cs.CVcited by 17

On the map: Diffusion models → Video generation

Abstract (arXiv)

Diffusion-based generative models have recently emerged as powerful solutions for high-quality synthesis in multiple domains. Leveraging the bidirectional Markov chains, diffusion probabilistic models generate samples by inferring the reversed Markov chain based on the learned distribution mapping at the forward diffusion process. In this work, we propose Modiff, a conditional paradigm that benefits from the denoising diffusion probabilistic model (DDPM) to tackle the problem of realistic and diverse action-conditioned 3D skeleton-based motion generation. We are a pioneering attempt that uses DDPM to synthesize a variable number of motion sequences conditioned on a categorical action. We evaluate our approach on the large-scale NTU RGB+D dataset and show improvements over state-of-the-art motion generation methods.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 33 of its 45 references that are in the map. First posted on arXiv 10 Jan 2023.

Builds on

33 of 45 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Human Motion Diffusion Model29 Sep
  2. 2022Denoising Diffusion Probabilistic Models for Styled Walking Synthesis29 Sep
  3. 2022FLAME: Free-form Language-based Motion Synthesis & Editing1 Sep
  4. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug

Other references · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  10. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  11. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  12. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
17 more
  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  2. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  3. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  4. 2021Robust Motion In-betweeningcited by 223
  5. 2019Learning Individual Styles of Conversational Gesturecited by 190
  6. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  7. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  8. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  9. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  10. 2021Single-Shot Motion Completion with Transformercited by 59
  11. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  12. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  13. 2021Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learningcited by 58
  14. 2021Adversarial Parametric Pose Priorcited by 38
  15. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  16. 2021Generative Adversarial Graph Convolutional Networks for Human Action Synthesiscited by 23
  17. 2021Action2video: Generating Videos of Human 3D Actionscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 4; 2025: 4; 2026: 1.

17 papers.

Sort:

By area:

  1. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
  2. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  3. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  4. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  5. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  6. 2023DPoser: Diffusion Model as Robust 3D Human Pose Priorcited by 17
  7. 2023Example-based Motion Synthesis via Generative Motion Matchingcited by 16
  8. 2023LongDanceDiff: Long-term Dance Generation with Conditional Diffusion Modelcited by 12
  9. 2023BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamicscited by 7
  10. 2024CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generationcited by 4
  11. 2025HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidancecited by 4
  12. 2025SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectoriescited by 3
5 more
  1. 2024Diffusion-based Graph Generative Methodscited by 2
  2. 2024SMGDiff: Soccer Motion Generation using diffusion probabilistic modelscited by 2
  3. 2025SPG: Improving Motion Diffusion by Smooth Perturbation Guidancecited by 2
  4. 2025Kinetic Mining in Context: Few-Shot Action Synthesis via Text-to-Motion Distillationcited by 0
  5. 2026OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models
  2. 2022Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
  3. 2023TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis
  4. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation
  5. 2023Single Motion Diffusion
  6. 2025Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising
  7. 2022Diffusion Probabilistic Modeling for Video Generation
  8. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models