mlsanityData to 7 Oct 2026

FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

arXiv 2202.12972 ↗First posted 25 Feb 2022cs.CV cs.GR cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

We present Face Swapping GAN (FSGAN) for face swapping and reenactment. Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training on those faces. We derive a novel iterative deep learning--based approach for face reenactment which adjusts significant pose and expression variations that can be applied to a single image or a video sequence. For video sequences, we introduce a continuous interpolation of the face views based on reenactment, Delaunay Triangulation, and barycentric coordinates. Occluded face regions are handled by a face completion network. Finally, we use a face blending network for seamless blending of the two faces while preserving the target skin color and lighting conditions. This network uses a novel Poisson blending loss combining Poisson optimization with a perceptual loss. We compare our approach to existing state-of-the-art systems and show our results to be both qualitatively and quantitatively superior. This work describes extensions of the FSGAN method, proposed in an earlier conference version of our work, as well as additional experiments and results.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 51 of its 83 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

51 of 83 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2014Conditional Generative Adversarial Netscited by 2,152
  12. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
38 more
  1. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  2. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  3. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  4. 2016Least Squares Generative Adversarial Networkscited by 1,000
  5. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  6. 2017Wasserstein GANcited by 635
  7. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  8. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  9. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
  10. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  11. 2018Deep Video Portraitscited by 265
  12. 2019Neural Voice Puppetry: Audio-driven Facial Reenactmentcited by 249
  13. 2019FaceShifter: Towards High Fidelity And Occlusion Aware Face Swappingcited by 221
  14. 2017Fine-Grained Head Pose Estimation Without Keypointscited by 163
  15. 2020Two-branch Recurrent Network for Isolating Deepfakes in Videoscited by 161
  16. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  17. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  18. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  19. 2019CARAFE: Content-Aware ReAssembly of FEaturescited by 119
  20. 2020Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatarscited by 116
  21. 2018DSFD: Dual Shot Face Detectorcited by 115
  22. 2019Text-based Editing of Talking-head Videocited by 102
  23. 2019Indices Matter: Learning to Index for Deep Image Mattingcited by 93
  24. 2019MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targetscited by 90
  25. 2018ReenactGAN: Learning to Reenact Faces via Boundary Transfercited by 85
  26. 2017On Face Segmentation, Face Swapping, and Face Perceptioncited by 71
  27. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  28. 2020img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimationcited by 57
  29. 2020DeepFake Detection Based on the Discrepancy Between the Face and its Contextcited by 56
  30. 2018RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spacescited by 50
  31. 2019Neural Style-Preserving Visual Dubbingcited by 47
  32. 2018A Compact Embedding for Facial Expression Similaritycited by 41
  33. 2018ExpNet: Landmark-Free, Deep, 3D Facial Expressionscited by 29
  34. 2018FSNet: An Identity-Aware Generative Model for Image-based Face Swappingcited by 29
  35. 2018CR-GAN: Learning Complete Representations for Multi-view Generationcited by 23
  36. 2017FacePoseNet: Making a Case for Landmark-Free Face Alignmentcited by 21
  37. 2020Iterative Text-based Editing of Talking-heads Using Neural Retargetingcited by 21
  38. 2018Triple consistency loss for pairing distributions in GAN-based face synthesiscited by 4

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 12; 2025: 8; 2026: 2.

33 papers.

Sort:

By area:

  1. 2022Fine-Grained Face Swapping via Regional GAN Inversioncited by 67
  2. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  3. 2023High-Fidelity and Freely Controllable Talking Head Video Generationcited by 42
  4. 2024Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detectioncited by 30
  5. 2023Contrastive Pseudo Learning for Open-World DeepFake Attributioncited by 27
  6. 2025CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulationcited by 16
  7. 2023A Generalist FaceX via Learning Unified Facial Representationcited by 13
  8. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  9. 2026DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformercited by 9
  10. 2023E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversioncited by 8
  11. 2025Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detectioncited by 8
  12. 2022GOTCHA: Real-Time Video Deepfake Detection via Challenge-Responsecited by 5
21 more
  1. 2022Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglementcited by 4
  2. 2025Evaluating Deepfake Detectors in the Wildcited by 3
  3. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  4. 2024Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detectorcited by 2
  5. 2025Do DeepFake Attribution Models Generalize?cited by 2
  6. 2025Controllable and Expressive One-Shot Video Head Swappingcited by 2
  7. 2025Visual Language Models as Zero-Shot Deepfake Detectorscited by 2
  8. 2024The Tug-of-War Between Deepfake Generation and Detectioncited by 1
  9. 2024Shaking the Fake: Detecting Deepfake Videos in Real Time via Active Probescited by 1
  10. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  11. 2023GMTR: Graph Matching Transformerscited by 0
  12. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  13. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  14. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  15. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  16. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  17. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  18. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  19. 20253D Engine-ready Photorealistic Avatars via Dynamic Texturescited by 0
  20. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  21. 2026Towards Generalizable Deepfake Detection via Real Distribution Bias Correctioncited by 0