FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping

TL;DR

FaceShifter introduces a two-stage face swapping framework that achieves high fidelity and occlusion awareness by integrating target attributes adaptively and refining results with a self-supervised error correction network.

Contribution

The paper presents a novel two-stage face swapping method with an attribute encoder, adaptive denormalization, and a self-supervised refinement network for occlusion handling.

Findings

Outperforms state-of-the-art methods in perceptual quality.

Better identity preservation in face swapping.

Effective occlusion handling with HEAR-Net.

Abstract

In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods.