FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images

TL;DR

FuseAnyPart introduces a diffusion-based method for customizable facial parts swapping using multiple reference images, enabling fine-grained face editing with high quality and robustness.

Contribution

It presents a novel fusion and injection framework for facial parts swapping in diffusion models, addressing the limitations of existing full-face swapping methods.

Findings

Outperforms existing methods in qualitative and quantitative evaluations.

Demonstrates high robustness and flexibility in facial parts swapping.

Enables seamless customization of facial features from multiple references.

Abstract

Facial parts swapping aims to selectively transfer regions of interest from the source image onto the target image while maintaining the rest of the target image unchanged. Most studies on face swapping designed specifically for full-face swapping, are either unable or significantly limited when it comes to swapping individual facial parts, which hinders fine-grained and customized character designs. However, designing such an approach specifically for facial parts swapping is challenged by a reasonable multiple reference feature fusion, which needs to be both efficient and effective. To overcome this challenge, FuseAnyPart is proposed to facilitate the seamless "fuse-any-part" customization of the face. In FuseAnyPart, facial parts from different people are assembled into a complete face in latent space within the Mask-based Fusion Module. Subsequently, the consolidated feature is dispatched to the Addition-based Injection Module for fusion within the UNet of the diffusion model to create novel characters. Extensive experiments qualitatively and quantitatively validate the superiority and robustness of FuseAnyPart. Source codes are available at https://github.com/Thomas-wyh/FuseAnyPart.