MobileFaceSwap: A Lightweight Framework for Video Face Swapping

TL;DR

MobileFaceSwap introduces a lightweight, real-time face swapping framework optimized for mobile devices, utilizing dynamic neural networks and knowledge distillation to achieve high-quality results with minimal parameters.

Contribution

The paper presents a novel lightweight identity-aware dynamic network for face swapping that is efficient enough for mobile deployment, with innovative modules and training strategies.

Findings

Contains only 0.50M parameters and requires 0.33G FLOPs per frame.

Achieves comparable results with state-of-the-art methods.

Enables real-time face swapping on mobile phones.

Abstract

Advanced face swapping methods have achieved appealing results. However, most of these methods have many parameters and computations, which makes it challenging to apply them in real-time applications or deploy them on edge devices like mobile phones. In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information. In particular, we design an efficient Identity Injection Module (IIM) by introducing two dynamic neural network techniques, including the weights prediction and weights modulation. Once the IDN is updated, it can be applied to swap faces given any target image or video. The presented IDN contains only 0.50M parameters and needs 0.33G FLOPs per frame, making it capable for real-time video face swapping on mobile phones. In addition, we introduce a knowledge distillation-based method for stable training, and a loss reweighting module is employed to obtain better synthesized results. Finally, our method achieves comparable results with the teacher models and other state-of-the-art methods.