菜单

关于 🐙 GitHub
arXiv 提交日期: 2026-05-04
📄 Abstract - IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration

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.

顶级标签: computer vision multi-modal machine learning
详细标签: face restoration identity preservation asymmetric conditioning reference-aware blind restoration 或 搜索:

IConFace:基于身份-结构非对称条件化的统一参考感知人脸修复 / IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration


1️⃣ 一句话总结

本文提出一种统一的参考感知人脸修复框架,通过非对称地处理身份信息和结构信息,既能利用参考图像提升细节恢复和身份一致性,又能在无参考时自动退化为普通盲修复,避免因参考图像差异导致的过度融合问题。

源自 arXiv: 2605.02814