mlsanityData to 7 Oct 2026

High-Fidelity and Arbitrary Face Editing

arXiv 2103.15814 ↗First posted 29 Mar 2021cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

Cycle consistency is widely used for face editing. However, we observe that the generator tends to find a tricky way to hide information from the original image to satisfy the constraint of cycle consistency, making it impossible to maintain the rich details (e.g., wrinkles and moles) of non-editing areas. In this work, we propose a simple yet effective method named HifaFace to address the above-mentioned problem from two perspectives. First, we relieve the pressure of the generator to synthesize rich details by directly feeding the high-frequency information of the input image into the end of the generator. Second, we adopt an additional discriminator to encourage the generator to synthesize rich details. Specifically, we apply wavelet transformation to transform the image into multi-frequency domains, among which the high-frequency parts can be used to recover the rich details. We also notice that a fine-grained and wider-range control for the attribute is of great importance for face editing. To achieve this goal, we propose a novel attribute regression loss. Powered by the proposed framework, we achieve high-fidelity and arbitrary face editing, outperforming other state-of-the-art approaches.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

38 of 49 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
26 more
  1. 2018Self-Attention Generative Adversarial Networkscited by 809
  2. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  3. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  4. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  5. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  6. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  7. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  8. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  9. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  10. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  11. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
  12. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  13. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 119
  14. 2016Learning Dense Correspondence via 3D-guided Cycle Consistencycited by 91
  15. 2018Towards Open-Set Identity Preserving Face Synthesiscited by 74
  16. 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
  17. 2017CycleGAN, a Master of Steganographycited by 63
  18. 2019Mask-Guided Portrait Editing with Conditional GANscited by 61
  19. 2019RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributescited by 56
  20. 2019Artistic Glyph Image Synthesis via One-Stage Few-Shot Learningcited by 53
  21. 2020GIQA: Generated Image Quality Assessmentcited by 51
  22. 2015Multi-Image Matching via Fast Alternating Minimizationcited by 33
  23. 2020CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Featurecited by 20
  24. 2020Attribute2Font: Creating Fonts You Want From Attributescited by 12
  25. 2020CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editingcited by 8
  26. 2020A recurrent cycle consistency loss for progressive face-to-face synthesiscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 9; 2024: 6; 2025: 3; 2026: 2.

35 papers.

Sort:

By area:

  1. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  2. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 116
  3. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  4. 2022AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatarscited by 46
  5. 2023Evading DeepFake Detectors via Adversarial Statistical Consistencycited by 37
  6. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  7. 2023Diverse Inpainting and Editing with GAN Inversioncited by 20
  8. 2022VecGAN: Image-to-Image Translation with Interpretable Latent Directionscited by 17
  9. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  10. 2022GAN-based Facial Attribute Manipulationcited by 16
  11. 2023Learning to Distill Global Representation for Sparse-View CTcited by 14
  12. 2022Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Datacited by 11
23 more
  1. 2023Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generationcited by 9
  2. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  3. 2022Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generationcited by 8
  4. 2023Face Identity-Aware Disentanglement in StyleGANcited by 8
  5. 2024Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Videocited by 8
  6. 2021PluGeN: Multi-Label Conditional Generation From Pre-Trained Modelscited by 5
  7. 2022Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenariocited by 5
  8. 2021US-GAN: On the importance of Ultimate Skip Connection for Facial Expression Synthesiscited by 4
  9. 2023SARGAN: Spatial Attention-based Residuals for Facial Expression Manipulationcited by 3
  10. 2021Causal Representation Learning for Context-Aware Face Transfercited by 2
  11. 2025Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Controlcited by 2
  12. 2022Study of detecting behavioral signatures within DeepFake videoscited by 1
  13. 2024Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learningcited by 1
  14. 2025Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Facescited by 1
  15. 2022StyleRes: Transforming the Residuals for Real Image Editing with StyleGANcited by 0
  16. 2023Both Spatial and Frequency Cues Contribute to High-Fidelity Image Inpaintingcited by 0
  17. 2023Improving Few-shot Image Generation by Structural Discrimination and Textural Modulationcited by 0
  18. 2024UP-FacE: User-predictable Fine-grained Face Shape Editingcited by 0
  19. 2024HAIFAI: Human-AI Interaction for Mental Face Reconstructioncited by 0
  20. 2024StyleAutoEncoder for manipulating image attributes using pre-trained StyleGANcited by 0
  21. 2025Efficient Few-shot Identity Preserving Attribute Editing for 3D-aware Deep Generative Modelscited by 0
  22. 2026LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulationcited by 0
  23. 2026AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editingcited by 0