mlsanityData to 13 Oct 2026

Motion Representations for Articulated Animation

arXiv 2104.11280 ↗First posted 22 Apr 2021cs.CVcited by 254

Not on the map. Why?

Cited by 64 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by considering their principal axes. In contrast to the previous keypoint-based works, our method extracts meaningful and consistent regions, describing locations, shape, and pose. The regions correspond to semantically relevant and distinct object parts, that are more easily detected in frames of the driving video. To force decoupling of foreground from background, we model non-object related global motion with an additional affine transformation. To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space. Our model can animate a variety of objects, surpassing previous methods by a large margin on existing benchmarks. We present a challenging new benchmark with high-resolution videos and show that the improvement is particularly pronounced when articulated objects are considered, reaching 96.6% user preference vs. the state of the art.

Key facts. Cited by 254 papers in the map (data through 13 Oct 2026). Builds on 37 of its 44 references that are in the map. First posted on arXiv 22 Apr 2021.

Builds on

37 of 44 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,687
  4. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,178
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,062
  6. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 785
  7. 2017VoxCeleb: a large-scale speaker identification datasetcited by 719
  8. 2020First Order Motion Model for Image Animationcited by 702
  9. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  10. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  11. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  12. 2018Video-to-Video Synthesiscited by 390
25 more
  1. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 320
  2. 2018Everybody Dance Nowcited by 314
  3. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  4. 2018Deep Video Portraitscited by 267
  5. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 220
  6. 2018Animating Arbitrary Objects via Deep Motion Transfercited by 207
  7. 2016Temporal Generative Adversarial Nets with Singular Value Clippingcited by 198
  8. 2019Few-shot Video-to-Video Synthesiscited by 197
  9. 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
  10. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  11. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  12. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  13. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  14. 2019MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targetscited by 90
  15. 2018Recycle-GAN: Unsupervised Video Retargetingcited by 89
  16. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  17. 2021Playable Video Generationcited by 64
  18. 20193D Guided Fine-Grained Face Manipulationcited by 45
  19. 2019Unsupervised Keypoint Learning for Guiding Class-Conditional Video Predictioncited by 36
  20. 2019Make a Face: Towards Arbitrary High Fidelity Face Manipulationcited by 29
  21. 2020Motion-supervised Co-Part Segmentationcited by 28
  22. 2018Every Smile is Unique: Landmark-Guided Diverse Smile Generationcited by 23
  23. 2019Vid2Game: Controllable Characters Extracted from Real-World Videoscited by 18
  24. 2020Human Motion Transfer from Poses in the Wildcited by 17
  25. 2019Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 8

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 3; 2022: 33; 2023: 44; 2024: 77; 2025: 71; 2026: 26.

254 papers.

Sort:

By area:

  1. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 685
  2. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 466
  3. 2022SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animationcited by 380
  4. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  5. 2023Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videoscited by 314
  6. 2024Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidancecited by 271
  7. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 247
  8. 2022Thin-Plate Spline Motion Model for Image Animationcited by 209
  9. 2024Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modelingcited by 209
  10. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 204
  11. 2024MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidancecited by 198
  12. 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 180
38 more
  1. 2022Latent Image Animator: Learning to Animate Images via Latent Space Navigationcited by 173
  2. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  3. 2023DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusioncited by 167
  4. 2023DisCo: Disentangled Control for Realistic Human Dance Generationcited by 142
  5. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 129
  6. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 128
  7. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 127
  8. 2023MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusioncited by 117
  9. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 116
  10. 2024UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animationcited by 102
  11. 2024Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependencycited by 102
  12. 2023Motion-Conditioned Diffusion Model for Controllable Video Synthesiscited by 99
  13. 2025Controllable Video Generation: A Surveycited by 95
  14. 2023Generative Image Dynamicscited by 94
  15. 2024X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attentioncited by 89
  16. 2024StableAnimator: High-Quality Identity-Preserving Human Image Animationcited by 88
  17. 2024MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Modelcited by 87
  18. 2024Animate-X: Universal Character Image Animation with Enhanced Motion Representationcited by 87
  19. 2025Wan-Animate: Unified Character Animation and Replacement with Holistic Replicationcited by 79
  20. 2023One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Fieldcited by 68
  21. 2023OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Renderingcited by 67
  22. 2023AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidancecited by 66
  23. 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animationcited by 63
  24. 2023Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generationcited by 61
  25. 2025Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordancecited by 61
  26. 2024Magic-Me: Identity-Specific Video Customized Diffusioncited by 59
  27. 2023MotionEditor: Editing Video Motion via Content-Aware Diffusioncited by 57
  28. 2022Audio-Driven Co-Speech Gesture Video Generationcited by 54
  29. 2024Follow-Your-Click: Open-domain Regional Image Animation via Short Promptscited by 52
  30. 2022SPACE: Speech-driven Portrait Animation with Controllable Expressioncited by 49
  31. 2022Implicit Warping for Animation with Image Setscited by 45
  32. 2023High-Fidelity and Freely Controllable Talking Head Video Generationcited by 42
  33. 2024Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesiscited by 41
  34. 2023LEO: Generative Latent Image Animator for Human Video Synthesiscited by 40
  35. 2024A Survey of Mambacited by 39
  36. 2024CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attentioncited by 39
  37. 2025HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generationcited by 39
  38. 2022Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioningcited by 37

50 most cited of 254 All 254 (JSON)