Robust ID-Specific Face Restoration via Alignment Learning

TL;DR

This paper introduces RIDFR, a diffusion model-based framework for face restoration that enhances identity fidelity and robustness by aligning multiple reference images to suppress irrelevant face semantics.

Contribution

The paper proposes a novel ID-specific face restoration method using diffusion models with alignment learning to improve identity preservation and robustness.

Findings

Outperforms state-of-the-art face restoration methods.

Reconstructs high-quality, identity-preserving face images.

Demonstrates robustness against various degradation and pose variations.

Abstract

The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs and stochastic generative processes remains unresolved. To address this challenge, we present Robust ID-Specific Face Restoration (RIDFR), a novel ID-specific face restoration framework based on diffusion models. Specifically, RIDFR leverages a pre-trained diffusion model in conjunction with two parallel conditioning modules. The Content Injection Module inputs the severely degraded image, while the Identity Injection Module integrates the specific identity from a given image. Subsequently, RIDFR incorporates Alignment Learning, which aligns the restoration results from multiple references with the same identity in order to suppress the interference of ID-irrelevant face semantics (e.g. pose, expression, make-up, hair style). Experiments demonstrate that our framework outperforms the state-of-the-art methods, reconstructing high-quality ID-specific results with high identity fidelity and demonstrating strong robustness.