Towards High Fidelity Face Swapping: A Comprehensive Survey and New Benchmark

TL;DR

This paper offers a comprehensive survey and benchmark for face swapping, organizing existing methods, introducing a new high-quality dataset, and establishing standardized evaluation protocols to advance the field.

Contribution

It provides a structured review of face swapping paradigms, introduces CASIA FaceSwapping benchmark, and offers a unified evaluation framework for future research.

Findings

Extensive experiments reveal performance strengths and limitations of current face swapping methods.

The new benchmark enables fair and controlled evaluation across diverse demographic and attribute variations.

Standardized protocols facilitate consistent comparison and development of robust face swapping techniques.

Abstract

Face swapping has witnessed significant progress in recent years, largely driven by advances in deep generative models such as GANs and diffusion models.Despite these advances, existing methods remain fragmented across different paradigms, and their evaluation is highly inconsistent due to the lack of standardized datasets and protocols. Moreover, prior surveys primarily focus on broader deepfake generation or detection, leaving face swapping insufficiently studied as a standalone problem. In this paper, we present a comprehensive survey and benchmark for face swapping. We provide a structured review of existing methods, organizing them into five major paradigms and systematically analyzing their design principles, strengths, and limitations. To enable fair and controlled evaluation, we introduce CASIA FaceSwapping, a high-quality benchmark with balanced demographic distributions and explicit attribute variations, and establish standardized protocols to assess the robustness of different face swapping methods. Extensive experiments on representative approaches yield new insights into the performance characteristics and limitations of current techniques. Overall, our work provides a unified perspective and a principled evaluation framework to facilitate the development of more robust and controllable face swapping methods. More results can be found at https://github.com/CASIA-NLPRAI/face-swapping-survey.