mlsanityData to 14 Oct 2026

GHOST 2.0: generative high-fidelity one shot transfer of heads

arXiv 2502.18417 ↗First posted 25 Feb 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

While the task of face swapping has recently gained attention in the research community, a related problem of head swapping remains largely unexplored. In addition to skin color transfer, head swap poses extra challenges, such as the need to preserve structural information of the whole head during synthesis and inpaint gaps between swapped head and background. In this paper, we address these concerns with GHOST 2.0, which consists of two problem-specific modules. First, we introduce enhanced Aligner model for head reenactment, which preserves identity information at multiple scales and is robust to extreme pose variations. Secondly, we use a Blender module that seamlessly integrates the reenacted head into the target background by transferring skin color and inpainting mismatched regions. Both modules outperform the baselines on the corresponding tasks, allowing to achieve state of the art results in head swapping. We also tackle complex cases, such as large difference in hair styles of source and target. Code is available at https://github.com/ai-forever/ghost-2.0

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 58 of its 74 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

58 of 74 references.

References · 58

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
38 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  2. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  3. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  4. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  5. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  6. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  7. 2020First Order Motion Model for Image Animationcited by 704
  8. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  9. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  10. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  11. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 436
  12. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
  13. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
  14. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  15. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  16. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  17. 2022Thin-Plate Spline Motion Model for Image Animationcited by 210
  18. 2021PIRenderer: Controllable Portrait Image Generation via Semantic Neural Renderingcited by 203
  19. 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
  20. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
  21. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 178
  22. 2022Latent Image Animator: Learning to Animate Images via Latent Space Navigationcited by 175
  23. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  24. 2022Instant Volumetric Head Avatarscited by 159
  25. 2020DeepFaceLab: Integrated, flexible and extensible face-swapping frameworkcited by 131
  26. 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
  27. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  28. 2020Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatarscited by 118
  29. 2020Neural Head Reenactment with Latent Pose Descriptorscited by 106
  30. 2021One Shot Face Swapping on Megapixelscited by 105
  31. 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesiscited by 97
  32. 2021HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swappingcited by 92
  33. 2024GPAvatar: Generalizable and Precise Head Avatar from Image(s)cited by 74
  34. 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
  35. 2022MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptationcited by 69
  36. 2023OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Renderingcited by 67
  37. 2024EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatarscited by 66
  38. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluationcited by 0
  2. 2026UniBioTransfer: A Unified Framework for Multiple Biometrics Transfercited by 0
  3. 2026CIPHER: Counterfeit Image Pattern High-level Examination via Representationcited by 0
  4. 2026AHS: Adaptive Head Synthesis via Synthetic Data Augmentationscited by 0
  5. 2026Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITScited by 0