SimSwap: An Efficient Framework For High Fidelity Face Swapping

TL;DR

SimSwap is a fast and versatile face swapping framework that transfers identities between faces while maintaining facial attributes, outperforming previous methods in generalization and attribute preservation.

Contribution

Introduces the ID Injection Module and Weak Feature Matching Loss to enable arbitrary face swapping with high fidelity and attribute preservation.

Findings

Achieves competitive identity transfer performance.

Better attribute preservation than previous methods.

Effective on wild face images.

Abstract

We propose an efficient framework, called Simple Swap (SimSwap), aiming for generalized and high fidelity face swapping. In contrast to previous approaches that either lack the ability to generalize to arbitrary identity or fail to preserve attributes like facial expression and gaze direction, our framework is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face. We overcome the above defects in the following two ways. First, we present the ID Injection Module (IIM) which transfers the identity information of the source face into the target face at feature level. By using this module, we extend the architecture of an identity-specific face swapping algorithm to a framework for arbitrary face swapping. Second, we propose the Weak Feature Matching Loss which efficiently helps our framework to preserve the facial attributes in an implicit way. Extensive experiments on wild faces demonstrate that our SimSwap is able to achieve competitive identity performance while preserving attributes better than previous state-of-the-art methods. The code is already available on github: https://github.com/neuralchen/SimSwap.