# High-resolution Face Swapping via Latent Semantics Disentanglement

arXiv: https://arxiv.org/abs/2203.15958 · HTML: https://mlsanity.com/paper/2203.15958/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 30 of 36)

- [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)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [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)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [Video Frame Synthesis using Deep Voxel Flow](https://mlsanity.com/paper/1702.02463/) (2017)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution](https://mlsanity.com/paper/2012.00739/) (2020)
- [Quadratic video interpolation](https://mlsanity.com/paper/1911.00627/) (2019)
- [Fast Face-swap Using Convolutional Neural Networks](https://mlsanity.com/paper/1611.09577/) (2016)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [One Shot Face Swapping on Megapixels](https://mlsanity.com/paper/2105.04932/) (2021)

## Built on by (most cited first, 30 of 57)

- [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022)
- [Fine-Grained Face Swapping via Regional GAN Inversion](https://mlsanity.com/paper/2211.14068/) (2022)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [BlendFace: Re-designing Identity Encoders for Face-Swapping](https://mlsanity.com/paper/2307.10854/) (2023)
- [Exploiting Style Latent Flows for Generalizing Deepfake Video Detection](https://mlsanity.com/paper/2403.06592/) (2024)
- [StyleSwap: Style-Based Generator Empowers Robust Face Swapping](https://mlsanity.com/paper/2209.13514/) (2022)
- [Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models](https://mlsanity.com/paper/2409.07269/) (2024)
- [G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors](https://mlsanity.com/paper/2408.09458/) (2024)
- [ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer](https://mlsanity.com/paper/2408.03284/) (2024)
- [Editing Out-of-domain GAN Inversion via Differential Activations](https://mlsanity.com/paper/2207.08134/) (2022)
- [A Generalist FaceX via Learning Unified Facial Representation](https://mlsanity.com/paper/2401.00551/) (2023)
- [HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping](https://mlsanity.com/paper/2212.06458/) (2022)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning](https://mlsanity.com/paper/2402.02003/) (2024)
- [MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection](https://mlsanity.com/paper/2409.09724/) (2024)
- [Reinforced Disentanglement for Face Swapping without Skip Connection](https://mlsanity.com/paper/2307.07928/) (2023)
- [DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning](https://mlsanity.com/paper/2504.14509/) (2025)
- [Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator](https://mlsanity.com/paper/2305.02594/) (2023)
- [Face De-identification: State-of-the-art Methods and Comparative Studies](https://mlsanity.com/paper/2411.09863/) (2024)
- [HiFiVFS: High Fidelity Video Face Swapping](https://mlsanity.com/paper/2411.18293/) (2024)
- [Disguise without Disruption: Utility-Preserving Face De-Identification](https://mlsanity.com/paper/2303.13269/) (2023)
- [ReliableSwap: Boosting General Face Swapping Via Reliable Supervision](https://mlsanity.com/paper/2306.05356/) (2023)
- [E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion](https://mlsanity.com/paper/2310.15081/) (2023)
- [FaceShield: Defending Facial Image against Deepfake Threats](https://mlsanity.com/paper/2412.09921/) (2024)
- [FlowFace: Semantic Flow-guided Shape-aware Face Swapping](https://mlsanity.com/paper/2212.02797/) (2022)
- [Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection](https://mlsanity.com/paper/2303.18174/) (2023)
- [3D-Aware Adversarial Makeup Generation for Facial Privacy Protection](https://mlsanity.com/paper/2306.14640/) (2023)
- [Multimodal Fake News Detection: MFND Dataset and Shallow-Deep Multitask Learning](https://mlsanity.com/paper/2505.06796/) (2025)
- [SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder](https://mlsanity.com/paper/2402.07370/) (2024)

## Abstract (arXiv)

We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure attributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending to produce a plausible swapping result. We further extend our method to video face swapping by enforcing two spatio-temporal constraints on the latent space and the image space. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art image/video face swapping methods in terms of hallucination quality and consistency. Code can be found at: https://github.com/cnnlstm/FSLSD_HiRes.