mlsanityData to 14 Oct 2026

FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping

arXiv 1912.13457 ↗First posted 31 Dec 2019cs.CVcited by 221

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods.

Key facts. Cited by 221 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 31; 2022: 44; 2023: 40; 2024: 36; 2025: 44; 2026: 26.

221 papers.

Sort:

By area:

  1. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  2. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 250
  3. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  4. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  5. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  6. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
  7. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 123
  8. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  9. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  10. 2021HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swappingcited by 92
  11. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  12. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
38 more
  1. 2022DiffFace: Diffusion-based Face Swapping with Facial Guidancecited by 77
  2. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  3. 2022MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptationcited by 69
  4. 2022Fine-Grained Face Swapping via Regional GAN Inversioncited by 67
  5. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 67
  6. 2024Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Controlcited by 67
  7. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  8. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  9. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 59
  10. 2023FaceStudio: Put Your Face Everywhere in Secondscited by 53
  11. 2021OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildcited by 50
  12. 2022Deepfake Detection: A Comprehensive Survey from the Reliability Perspectivecited by 50
  13. 2021ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Imagescited by 48
  14. 2024Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detectioncited by 47
  15. 2022Region-Aware Face Swappingcited by 45
  16. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 45
  17. 2022StyleSwap: Style-Based Generator Empowers Robust Face Swappingcited by 39
  18. 2024Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Modelscited by 36
  19. 2022On Improving Cross-dataset Generalization of Deepfake Detectorscited by 34
  20. 2022Explaining Deepfake Detection by Analysing Image Matchingcited by 34
  21. 2021E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversioncited by 33
  22. 2022FSGANv2: Improved Subject Agnostic Face Swapping and Reenactmentcited by 33
  23. 2021Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectorscited by 32
  24. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  25. 2023Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learningcited by 32
  26. 2021Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothnesscited by 30
  27. 2021StyleFusion: A Generative Model for Disentangling Spatial Segmentscited by 28
  28. 2022Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Eracited by 27
  29. 2023Contrastive Pseudo Learning for Open-World DeepFake Attributioncited by 27
  30. 2025Exploring Unbiased Deepfake Detection via Token-Level Shuffling and Mixingcited by 27
  31. 2024Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generationcited by 26
  32. 2022Restricted Black-box Adversarial Attack Against DeepFake Face Swappingcited by 25
  33. 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
  34. 2024CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Modelscited by 24
  35. 2021Deepfake Videos in the Wild: Analysis and Detectioncited by 23
  36. 2021DP-Image: Differential Privacy for Image Data in Feature Spacecited by 23
  37. 2022MINTIME: Multi-Identity Size-Invariant Video Deepfake Detectioncited by 23
  38. 2023DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Cluescited by 23

50 most cited of 221 All 221 (JSON)