mlsanityData to 14 Oct 2026

MoDi: Unconditional Motion Synthesis from Diverse Data

arXiv 2206.08010 ↗First posted 16 Jun 2022cs.GR cs.AI cs.CVcited by 59

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The emergence of neural networks has revolutionized the field of motion synthesis. Yet, learning to unconditionally synthesize motions from a given distribution remains challenging, especially when the motions are highly diverse. In this work, we present MoDi -- a generative model trained in an unsupervised setting from an extremely diverse, unstructured and unlabeled dataset. During inference, MoDi can synthesize high-quality, diverse motions. Despite the lack of any structure in the dataset, our model yields a well-behaved and highly structured latent space, which can be semantically clustered, constituting a strong motion prior that facilitates various applications including semantic editing and crowd simulation. In addition, we present an encoder that inverts real motions into MoDi's natural motion manifold, issuing solutions to various ill-posed challenges such as completion from prefix and spatial editing. Our qualitative and quantitative experiments achieve state-of-the-art results that outperform recent SOTA techniques. Code and trained models are available at https://sigal-raab.github.io/MoDi.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). Builds on 52 of its 75 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

52 of 75 references.

References · 52

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2018Demystifying MMD GANscited by 1,293
  9. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  10. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  11. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  12. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
38 more
  1. 2018Which Training Methods for GANs do actually Converge?cited by 679
  2. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  3. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  4. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  5. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  6. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  7. 2018Assessing Generative Models via Precision and Recallcited by 406
  8. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
  9. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 332
  10. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  11. 2021Robust Motion In-betweeningcited by 229
  12. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  13. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  14. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 124
  15. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  16. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  17. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  18. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  19. 2020Unpaired Motion Style Transfer from Video to Animationcited by 94
  20. 2018Neural Kinematic Networks for Unsupervised Motion Retargettingcited by 88
  21. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  22. 2020Convolutional Autoencoders for Human Motion Infillingcited by 73
  23. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  24. 2021Single-Shot Motion Completion with Transformercited by 59
  25. 2021Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structurecited by 53
  26. 2018Recurrent Transition Networks for Character Locomotioncited by 52
  27. 2019Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitionscited by 46
  28. 2019Learning Character-Agnostic Motion for Motion Retargeting in 2Dcited by 45
  29. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  30. 2020MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistencycited by 31
  31. 2020Structure-Aware Human-Action Generationcited by 28
  32. 2021Generative Adversarial Graph Convolutional Networks for Human Action Synthesiscited by 23
  33. 2022GANimator: Neural Motion Synthesis from a Single Sequencecited by 23
  34. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  35. 2020Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Modelcited by 16
  36. 2021MUGL: Large Scale Multi Person Conditional Action Generation with Locomotioncited by 14
  37. 2018Listen to Dance: Music-driven choreography generation using Autoregressive Encoder-Decoder Networkcited by 11
  38. 2021FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstructioncited by 11

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 14; 2024: 22; 2025: 15; 2026: 6.

59 papers.

Sort:

By area:

  1. 2022Human Motion Diffusion Modelcited by 1,080
  2. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  3. 2023Human Motion Diffusion as a Generative Priorcited by 357
  4. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  5. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 94
  6. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 89
  7. 2023Single Motion Diffusioncited by 65
  8. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 64
  9. 2023Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generationcited by 56
  10. 2024ParCo: Part-Coordinating Text-to-Motion Synthesiscited by 55
  11. 2024ReGenNet: Towards Human Action-Reaction Synthesiscited by 53
  12. 2024Generating Human Motion in 3D Scenes from Text Descriptionscited by 49
38 more
  1. 2023Motion Flow Matching for Human Motion Synthesis and Editingcited by 38
  2. 2023MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusioncited by 37
  3. 2024Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfercited by 31
  4. 2024InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusioncited by 28
  5. 2024HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Devicecited by 27
  6. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  7. 2025ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generationcited by 20
  8. 2024Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editingcited by 18
  9. 2023Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Modelscited by 17
  10. 2025UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generationcited by 17
  11. 2023Example-based Motion Synthesis via Generative Motion Matchingcited by 16
  12. 2024Tri-Modal Motion Retrieval by Learning a Joint Embedding Spacecited by 16
  13. 20233DiFACE: Diffusion-based Speech-driven 3D Facial Animation and Editingcited by 15
  14. 2025FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editingcited by 11
  15. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generationcited by 10
  16. 2024Constrained Diffusion with Trust Samplingcited by 10
  17. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  18. 2025ARFlow: Human Action-Reaction Flow Matching with Physical Guidancecited by 7
  19. 2025Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animationcited by 7
  20. 2023HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedbackcited by 6
  21. 2024CathAction: A Benchmark for Endovascular Intervention Understandingcited by 6
  22. 2024BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesiscited by 6
  23. 2024LS-GAN: Human Motion Synthesis with Latent-space GANscited by 5
  24. 2023FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptionscited by 4
  25. 2024Infinite Motion: Extended Motion Generation via Long Text Instructionscited by 4
  26. 2024Scalable Group Choreography via Variational Phase Manifold Learningcited by 4
  27. 20253DiFACE: Synthesizing and Editing Holistic 3D Facial Animationcited by 4
  28. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  29. 2024ViMo: Generating Motions from Casual Videoscited by 3
  30. 2025Versatile Multimodal Controls for Expressive Talking Human Animationcited by 3
  31. 2024Diffusion-based Graph Generative Methodscited by 2
  32. 2024SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformerscited by 2
  33. 2025SPG: Improving Motion Diffusion by Smooth Perturbation Guidancecited by 2
  34. 2025Generative Modeling of Shape-Dependent Self-Contact Human Posescited by 2
  35. 2025MoReact: Generating Reactive Motion from Textual Descriptionscited by 2
  36. 2025Unconditional Human Motion and Shape Generation via Balanced Score-Based Diffusioncited by 2
  37. 2024Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifoldcited by 1
  38. 2026ReactMotion: Generating Reactive Listener Motions from Speaker Utterancecited by 1

50 most cited of 59 All 59 (JSON)