mlsanityData to 14 Oct 2026

TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis

arXiv 2307.15042 ↗First posted 27 Jul 2023cs.CV cs.GRcited by 49

On the map: Diffusion models → Video generation

Abstract (arXiv)

The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain. In this work, we propose to adapt the gradual diffusion concept (operating along a diffusion time-axis) into the temporal-axis of the motion sequence. Our key idea is to extend the DDPM framework to support temporally varying denoising, thereby entangling the two axes. Using our special formulation, we iteratively denoise a motion buffer that contains a set of increasingly-noised poses, which auto-regressively produces an arbitrarily long stream of frames. With a stationary diffusion time-axis, in each diffusion step we increment only the temporal-axis of the motion such that the framework produces a new, clean frame which is removed from the beginning of the buffer, followed by a newly drawn noise vector that is appended to it. This new mechanism paves the way towards a new framework for long-term motion synthesis with applications to character animation and other domains.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 37 of its 60 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

37 of 60 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Human Motion Diffusion as a Generative Prior2 Mar
  2. 2022PhysDiff: Physics-Guided Human Motion Diffusion Model5 Dec
  3. 2022Human Motion Diffusion Model29 Sep
  4. 2022FLAME: Free-form Language-based Motion Synthesis & Editing1 Sep
  5. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  10. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  11. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  12. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
20 more
  1. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  2. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  3. 2014Show and Tell: A Neural Image Caption Generatorcited by 879
  4. 2015Unsupervised Learning of Video Representations using LSTMscited by 435
  5. 2022EDGE: Editable Dance Generation From Musiccited by 287
  6. 2021Robust Motion In-betweeningcited by 229
  7. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  8. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
  9. 2021Character Controllers Using Motion VAEscited by 184
  10. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 124
  11. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 109
  12. 2020Unpaired Motion Style Transfer from Video to Animationcited by 94
  13. 2014Video (language) modeling: a baseline for generative models of natural videoscited by 92
  14. 2018Neural Kinematic Networks for Unsupervised Motion Retargettingcited by 88
  15. 2022Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phasescited by 72
  16. 2021Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structurecited by 53
  17. 2019MoGlow: Probabilistic and controllable motion synthesis using normalising flowscited by 47
  18. 2019Learning Character-Agnostic Motion for Motion Retargeting in 2Dcited by 45
  19. 2022Real-time Controllable Motion Transition for Characterscited by 29
  20. 2023Example-based Motion Synthesis via Generative Motion Matchingcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 14; 2025: 17; 2026: 13.

49 papers.

Sort:

By area:

  1. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 182
  2. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 138
  3. 2024FIFO-Diffusion: Generating Infinite Videos from Text without Trainingcited by 137
  4. 2023State of the Art on Diffusion Models for Visual Computingcited by 127
  5. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 114
  6. 2023Controllable Human-Object Interaction Synthesiscited by 109
  7. 2024Rolling Diffusion Modelscited by 104
  8. 2023HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Modelscited by 93
  9. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 91
  10. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
  11. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 64
  12. 2024Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Modelscited by 56
37 more
  1. 2024One Diffusion to Generate Them Allcited by 41
  2. 2025Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectoriescited by 39
  3. 2025Absolute Coordinates Make Motion Generation Easycited by 29
  4. 2025Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Controlcited by 28
  5. 2024HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Devicecited by 27
  6. 2024ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generationcited by 25
  7. 2025SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Modelcited by 20
  8. 2024SCENIC: Scene-aware Semantic Navigation with Instruction-guided Controlcited by 13
  9. 2025Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Controlcited by 13
  10. 2025From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Modelscited by 11
  11. 2024FORCE: Physics-aware Human-object Interactioncited by 7
  12. 2025Zero-Shot Human-Object Interaction Synthesis with Multimodal Priorscited by 7
  13. 2026ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generationcited by 7
  14. 2025RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanningcited by 6
  15. 2025Compositional Flows for 3D Molecule and Synthesis Pathway Co-designcited by 6
  16. 2025HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidancecited by 6
  17. 2026Unleashing Guidance Without Classifiers for Human-Object Interaction Animationcited by 6
  18. 2026TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Sizecited by 5
  19. 2026ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planningcited by 5
  20. 2025Diffusion Forcing for Multi-Agent Interaction Sequence Modelingcited by 4
  21. 2024COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Modelscited by 3
  22. 2025PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Taskscited by 3
  23. 2025Rolling Ahead Diffusion for Traffic Scene Simulationcited by 2
  24. 2025Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learningcited by 2
  25. 2025MoReact: Generating Reactive Motion from Textual Descriptionscited by 2
  26. 2026Inference-Time Scaling in Diffusion Models through Iterative Partial Refinementcited by 2
  27. 2026TacForcing: Streaming Action Generation with Execution-Time Tactile Feedbackcited by 2
  28. 2026InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalizationcited by 1
  29. 2026DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcingcited by 1
  30. 2026GIRAF: Towards Generalizable Human Interactions with Articulated Objectscited by 1
  31. 2024RDM: Recurrent Diffusion Model for Human Motion Generationcited by 0
  32. 2025Step2Motion: Locomotion Reconstruction from Pressure Sensing Insolescited by 0
  33. 2025SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignmentcited by 0
  34. 2026FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesiscited by 0
  35. 2026EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcingcited by 0
  36. 2026PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Controlcited by 0
  37. 2026CleanMDM: Clean Motion Diffusion Model for Multimodal Motion Cleanupcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Controllable Longer Image Animation with Diffusion Models
  2. 2026Causal Motion Diffusion Models for Autoregressive Motion Generation
  3. 2024AnaMoDiff: 2D Analogical Motion Diffusion via Disentangled Denoising
  4. 2025Characterizing Motion Encoding in Video Diffusion Timesteps
  5. 2023Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models
  6. 2025Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising
  7. 2023Single Motion Diffusion
  8. 2024Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation