# High-resolution Face Swapping via Latent Semantics Disentanglement

Source: [High-resolution Face Swapping via Latent Semantics Disentanglement](<https://www.sota2.com/research/paper/68fa6c181e209131cea3221f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:14:32.298Z

Authors: Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He

Published: 2022-03-30T00:33:08.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Face Swapping on Face Swapping Evaluation Set (test)](<https://www.sota2.com/research/sota/face-swapping-on-face-swapping-evaluation-set-test.md>): Face Swapping; Face Swapping Evaluation Set (test); ID Retrieval Top-1 Acc: 5.

- [Face Swapping on FaceForensics++ (with Speed Measurement)](<https://www.sota2.com/research/sota/face-swapping-on-faceforensics-plus-plus-with-speed-measurement.md>): Face Swapping; FaceForensics++; ID Retrieval: 0.9005.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.15958>)

[PDF](<https://arxiv.org/pdf/2203.15958.pdf>)
