# High-Fidelity and Arbitrary Face Editing

arXiv: https://arxiv.org/abs/2103.15814 · HTML: https://mlsanity.com/paper/2103.15814/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 49 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss](https://mlsanity.com/paper/1708.00961/) (2017)
- [GANimation: Anatomically-aware Facial Animation from a Single Image](https://mlsanity.com/paper/1807.09251/) (2018)
- [STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing](https://mlsanity.com/paper/1904.09709/) (2019)
- [Learning Dense Correspondence via 3D-guided Cycle Consistency](https://mlsanity.com/paper/1604.05383/) (2016)
- [Towards Open-Set Identity Preserving Face Synthesis](https://mlsanity.com/paper/1803.11182/) (2018)
- [The Unusual Effectiveness of Averaging in GAN Training](https://mlsanity.com/paper/1806.04498/) (2018)
- [CycleGAN, a Master of Steganography](https://mlsanity.com/paper/1712.02950/) (2017)
- [Mask-Guided Portrait Editing with Conditional GANs](https://mlsanity.com/paper/1905.10346/) (2019)

## Built on by (most cited first, 30 of 35)

- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [Wavelet Diffusion Models are fast and scalable Image Generators](https://mlsanity.com/paper/2211.16152/) (2022)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars](https://mlsanity.com/paper/2210.06465/) (2022)
- [Evading DeepFake Detectors via Adversarial Statistical Consistency](https://mlsanity.com/paper/2304.11670/) (2023)
- [WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation](https://mlsanity.com/paper/2207.07288/) (2022)
- [Diverse Inpainting and Editing with GAN Inversion](https://mlsanity.com/paper/2307.15033/) (2023)
- [VecGAN: Image-to-Image Translation with Interpretable Latent Directions](https://mlsanity.com/paper/2207.03411/) (2022)
- [FreGAN: Exploiting Frequency Components for Training GANs under Limited Data](https://mlsanity.com/paper/2210.05461/) (2022)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [Learning to Distill Global Representation for Sparse-View CT](https://mlsanity.com/paper/2308.08463/) (2023)
- [Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data](https://mlsanity.com/paper/2203.10474/) (2022)
- [Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation](https://mlsanity.com/paper/2306.00914/) (2023)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video](https://mlsanity.com/paper/2412.11395/) (2024)
- [Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation](https://mlsanity.com/paper/2208.12550/) (2022)
- [Face Identity-Aware Disentanglement in StyleGAN](https://mlsanity.com/paper/2309.12033/) (2023)
- [PluGeN: Multi-Label Conditional Generation From Pre-Trained Models](https://mlsanity.com/paper/2109.09011/) (2021)
- [Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario](https://mlsanity.com/paper/2207.01906/) (2022)
- [US-GAN: On the importance of Ultimate Skip Connection for Facial Expression Synthesis](https://mlsanity.com/paper/2112.13002/) (2021)
- [SARGAN: Spatial Attention-based Residuals for Facial Expression Manipulation](https://mlsanity.com/paper/2303.17212/) (2023)
- [Causal Representation Learning for Context-Aware Face Transfer](https://mlsanity.com/paper/2110.01571/) (2021)
- [Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Control](https://mlsanity.com/paper/2507.03979/) (2025)
- [Study of detecting behavioral signatures within DeepFake videos](https://mlsanity.com/paper/2208.03561/) (2022)
- [Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning](https://mlsanity.com/paper/2403.08806/) (2024)
- [Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces](https://mlsanity.com/paper/2510.08067/) (2025)
- [StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN](https://mlsanity.com/paper/2212.14359/) (2022)
- [Both Spatial and Frequency Cues Contribute to High-Fidelity Image Inpainting](https://mlsanity.com/paper/2307.07678/) (2023)
- [Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation](https://mlsanity.com/paper/2308.16110/) (2023)
- [UP-FacE: User-predictable Fine-grained Face Shape Editing](https://mlsanity.com/paper/2403.13972/) (2024)

## 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.