Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention

TL;DR

This paper introduces Parallel Visual Attention (PVA) with diffusion models for face inpainting, achieving superior identity preservation, user-controlled attributes, and faster inference with minimal fine-tuning.

Contribution

The paper proposes PVA integrated into diffusion models, enabling efficient, identity-preserving face inpainting with semantic control and reduced computational requirements.

Findings

PVA outperforms benchmarks like MyStyle and Custom Diffusion in identity preservation.

PVA achieves over 20x faster fine-tuning for new identities.

PVA provides effective language-guided face inpainting.

Abstract

Face inpainting is important in various applications, such as photo restoration, image editing, and virtual reality. Despite the significant advances in face generative models, ensuring that a person's unique facial identity is maintained during the inpainting process is still an elusive goal. Current state-of-the-art techniques, exemplified by MyStyle, necessitate resource-intensive fine-tuning and a substantial number of images for each new identity. Furthermore, existing methods often fall short in accommodating user-specified semantic attributes, such as beard or expression. To improve inpainting results, and reduce the computational complexity during inference, this paper proposes the use of Parallel Visual Attention (PVA) in conjunction with diffusion models. Specifically, we insert parallel attention matrices to each cross-attention module in the denoising network, which attends to features extracted from reference images by an identity encoder. We train the added attention modules and identity encoder on CelebAHQ-IDI, a dataset proposed for identity-preserving face inpainting. Experiments demonstrate that PVA attains unparalleled identity resemblance in both face inpainting and face inpainting with language guidance tasks, in comparison to various benchmarks, including MyStyle, Paint by Example, and Custom Diffusion. Our findings reveal that PVA ensures good identity preservation while offering effective language-controllability. Additionally, in contrast to Custom Diffusion, PVA requires just 40 fine-tuning steps for each new identity, which translates to a significant speed increase of over 20 times.