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

2026-04-26

AI Summary

This work addresses the fragmented state of existing face swapping methods, which have historically lacked a unified evaluation framework and have not been systematically studied as an independent research task. To bridge this gap, the study formally establishes face swapping as a distinct research direction and introduces a structured taxonomy encompassing five methodological paradigms spanning both GANs and diffusion models. The authors further present CASIA FaceSwapping, a new benchmark dataset featuring balanced demographic distribution and explicit attribute variations, alongside a standardized evaluation protocol. Through extensive experiments, the paper comprehensively analyzes the performance and limitations of current approaches, thereby providing the community with a unified framework, a reliable benchmark, and clear directions for advancing high-fidelity face swapping research.

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.

Problem

• face swapping
• deep generative models
• evaluation benchmark
• standardized protocols
• deepfakes

Innovation

• face swapping
• benchmark dataset
• standardized evaluation
• deep generative models
• high fidelity