IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration
This work addresses the problem of identity preservation in blind face restoration for applications like forensics and photo enhancement, offering a unified model that handles both reference-available and reference-absent scenarios.
IConFace proposes an asymmetric conditioning framework for blind face restoration that uses same-identity references to improve identity consistency and detail recovery, while also functioning as a no-reference model when references are absent. The method achieves state-of-the-art performance on multiple benchmarks, outperforming prior works by up to 0.5 dB in PSNR.
Blind face restoration is highly ill-posed under severe degradation, where identity-critical details may be missing from the degraded input. Same-identity references reduce this ambiguity, but mismatched pose, expression, illumination, age, makeup, or local facial states can lead to overuse of reference appearance. We propose \textbf{IConFace}, a unified reference-aware and no-reference framework with identity--structure asymmetric conditioning. References are distilled into a norm-weighted global AdaFace identity anchor for image-only modulation, while the degraded image is reinforced as the spatial structure anchor through low-rank residuals and block-wise degraded cross-attention with two-route memory. The resulting single checkpoint exploits references when available and falls back to no-reference restoration when absent, improving identity consistency, fine-detail recovery, and degraded-only restoration quality in a unified model.