mlsanityData to 7 Oct 2026

Thin-Plate Spline Motion Model for Image Animation

arXiv 2203.14367 ↗First posted 27 Mar 2022cs.CVcited by 209

Not on the map. Why?

Cited by 53 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images. In this paper, a new end-to-end unsupervised motion transfer framework is proposed to overcome such issue. Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image. Secondly, in order to restore the missing regions more realistically, we leverage multi-resolution occlusion masks to achieve more effective feature fusion. Finally, additional auxiliary loss functions are designed to ensure that there is a clear division of labor in the network modules, encouraging the network to generate high-quality images. Our method can animate a variety of objects, including talking faces, human bodies, and pixel animations. Experiments demonstrate that our method performs better on most benchmarks than the state of the art with visible improvements in pose-related metrics.

Key facts. Cited by 209 papers in the map (data through 7 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 27 Mar 2022.

Builds on

31 of 37 references.

References · 31

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  4. 2016Pyramid Scene Parsing Networkcited by 2,472
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  7. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  8. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  9. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  10. 2020First Order Motion Model for Image Animationcited by 698
  11. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  12. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
19 more
  1. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  2. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  3. 2018Everybody Dance Nowcited by 313
  4. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  5. 2021Motion Representations for Articulated Animationcited by 253
  6. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  7. 2018Animating Arbitrary Objects via Deep Motion Transfercited by 206
  8. 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
  9. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  10. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  11. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  12. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  13. 2020HeadGAN: One-shot Neural Head Synthesis and Editingcited by 105
  14. 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
  15. 2019MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targetscited by 90
  16. 2015face anti-spoofing based on color texture analysiscited by 82
  17. 2021Deep Learning for Face Anti-Spoofing: A Surveycited by 64
  18. 2021High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Networkcited by 61
  19. 2017Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognitioncited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 37; 2024: 73; 2025: 69; 2026: 25.

209 papers.

Sort:

By area:

  1. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 683
  2. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 463
  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. 2024Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidancecited by 271
  6. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 202
  7. 2024MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidancecited by 196
  8. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 172
  9. 2024PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generationcited by 169
  10. 2023DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusioncited by 167
  11. 2023DisCo: Disentangled Control for Realistic Human Dance Generationcited by 141
  12. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 127
38 more
  1. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  2. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  3. 2023MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusioncited by 115
  4. 2024UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animationcited by 101
  5. 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesiscited by 97
  6. 2023Generative Image Dynamicscited by 93
  7. 2025Controllable Video Generation: A Surveycited by 93
  8. 2024X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attentioncited by 88
  9. 2024Animate-X: Universal Character Image Animation with Enhanced Motion Representationcited by 86
  10. 2025Wan-Animate: Unified Character Animation and Replacement with Holistic Replicationcited by 76
  11. 2023One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Fieldcited by 68
  12. 2023SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Facescited by 67
  13. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  14. 2024Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Controlcited by 66
  15. 2025PhysGen3D: Crafting a Miniature Interactive World from a Single Imagecited by 65
  16. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  17. 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animationcited by 63
  18. 2023Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generationcited by 61
  19. 2025Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordancecited by 60
  20. 2024Magic-Me: Identity-Specific Video Customized Diffusioncited by 58
  21. 2025HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animationcited by 55
  22. 2024VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesiscited by 48
  23. 2023DPE: Disentanglement of Pose and Expression for General Video Portrait Editingcited by 45
  24. 2023Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videoscited by 44
  25. 2023LivePhoto: Real Image Animation with Text-guided Motion Controlcited by 44
  26. 2023High-Fidelity and Freely Controllable Talking Head Video Generationcited by 42
  27. 2024Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesiscited by 41
  28. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 41
  29. 2025FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesiscited by 37
  30. 2025DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidancecited by 36
  31. 2024Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Modelcited by 34
  32. 2023VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactmentcited by 33
  33. 2024Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videoscited by 32
  34. 2025OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulationcited by 30
  35. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  36. 2024VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animationcited by 27
  37. 2024MegActor: Harness the Power of Raw Video for Vivid Portrait Animationcited by 27
  38. 2024Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Frameworkcited by 26

50 most cited of 209 All 209 (JSON)