LI-Net: Large-Pose Identity-Preserving Face Reenactment Network

TL;DR

LI-Net is a novel face reenactment network that effectively preserves identity and accurately reproduces expressions and poses, especially for large-pose faces, by disentangling and adjusting facial features.

Contribution

The paper introduces LI-Net, which uses landmark transformation and feature decoupling to improve large-pose face reenactment with identity preservation.

Findings

Outperforms existing methods in accuracy and visual quality.

Effectively handles large-pose face reenactment.

Demonstrates superior qualitative and quantitative results.

Abstract

Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously. Most existing methods directly apply driving facial landmarks to reenact source faces and ignore the intrinsic gap between two identities, resulting in the identity mismatch issue. Besides, they neglect the entanglement of expression and pose features when encoding driving faces, leading to inaccurate expressions and visual artifacts on large-pose reenacted faces. To address these problems, we propose a Large-pose Identity-preserving face reenactment network, LI-Net. Specifically, the Landmark Transformer is adopted to adjust driving landmark images, which aims to narrow the identity gap between driving and source landmark images. Then the Face Rotation Module and the Expression Enhancing Generator decouple the transformed landmark image into pose and expression features, and reenact those attributes separately to generate identity-preserving faces with accurate expressions and poses. Both qualitative and quantitative experimental results demonstrate the superiority of our method.