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

arXiv cs.CV / 5/5/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper surveys recent face-swapping progress and organizes existing approaches into five major paradigms, analyzing their design principles, strengths, and weaknesses.
It highlights that face-swapping research has lacked standardized datasets and evaluation protocols, leading to fragmented methods and highly inconsistent comparisons.
To address this, the authors introduce CASIA FaceSwapping, a high-quality benchmark with balanced demographic coverage and explicit attribute variations.
The study also establishes standardized assessment protocols and reports extensive experiments to characterize the performance, robustness, and limitations of current face-swapping techniques.
The authors position the survey and benchmark as a unified framework to support more robust and controllable face-swapping development.

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.