# Learning Disentangled Representation for One-shot Progressive Face Swapping

Source: [Learning Disentangled Representation for One-shot Progressive Face Swapping](<https://www.sota2.com/research/paper/68fa75e41e209131cea6a82e>)

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

Data updated: 2025-10-27T06:43:58.474Z

Authors: Qi Li, Weining Wang, Chengzhong Xu, Zhenan Sun, Ming-Hsuan Yang

Published: 2022-03-24T11:19:04.000Z

## Abstract

Although face swapping has attracted much attention in recent years, it remains a challenging problem. Existing methods leverage a large number of data samples to explore the intrinsic properties of face swapping without considering the semantic information of face images. Moreover, the representation of the identity information tends to be fixed, leading to suboptimal face swapping. In this paper, we present a simple yet efficient method named FaceSwapper, for one-shot face swapping based on Generative Adversarial Networks. Our method consists of a disentangled representation module and a semantic-guided fusion module. The disentangled representation module comprises an attribute encoder and an identity encoder, which aims to achieve the disentanglement of the identity and attribute information. The identity encoder is more flexible, and the attribute encoder contains more attribute details than its competitors. Benefiting from the disentangled representation, FaceSwapper can swap face images progressively. In addition, semantic information is introduced into the semantic-guided fusion module to control the swapped region and model the pose and expression more accurately. Experimental results show that our method achieves state-of-the-art results on benchmark datasets with fewer training samples. Our code is publicly available at https://github.com/liqi-casia/FaceSwapper.

## 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 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: 0.9448.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.12985>)

[PDF](<https://arxiv.org/pdf/2203.12985.pdf>)
