InfoBFR: Real-World Blind Face Restoration via Information Bottleneck

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Nan, Li, Jia, Huang, Huaibo, Shang, Ke, He, Ran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916584514125824
author Gao, Nan
Li, Jia
Huang, Huaibo
Shang, Ke
He, Ran
author_facet Gao, Nan
Li, Jia
Huang, Huaibo
Shang, Ke
He, Ran
contents Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns. Current BFR methods have realized certain restored productions but with inherent neural degradations that limit real-world generalization in complicated scenarios. In this paper, we propose a plug-and-play framework InfoBFR to tackle neural degradations, e.g., prior bias, topological distortion, textural distortion, and artifact residues, which achieves high-generalization face restoration in diverse wild and heterogeneous scenes. Specifically, based on the results from pre-trained BFR models, InfoBFR considers information compression using manifold information bottleneck (MIB) and information compensation with efficient diffusion LoRA to conduct information optimization. InfoBFR effectively synthesizes high-fidelity faces without attribute and identity distortions. Comprehensive experimental results demonstrate the superiority of InfoBFR over state-of-the-art GAN-based and diffusion-based BFR methods, with around 70ms consumption, 16M trainable parameters, and nearly 85% BFR-boosting. It is promising that InfoBFR will be the first plug-and-play restorer universally employed by diverse BFR models to conquer neural degradations.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15443
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InfoBFR: Real-World Blind Face Restoration via Information Bottleneck
Gao, Nan
Li, Jia
Huang, Huaibo
Shang, Ke
He, Ran
Computer Vision and Pattern Recognition
Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns. Current BFR methods have realized certain restored productions but with inherent neural degradations that limit real-world generalization in complicated scenarios. In this paper, we propose a plug-and-play framework InfoBFR to tackle neural degradations, e.g., prior bias, topological distortion, textural distortion, and artifact residues, which achieves high-generalization face restoration in diverse wild and heterogeneous scenes. Specifically, based on the results from pre-trained BFR models, InfoBFR considers information compression using manifold information bottleneck (MIB) and information compensation with efficient diffusion LoRA to conduct information optimization. InfoBFR effectively synthesizes high-fidelity faces without attribute and identity distortions. Comprehensive experimental results demonstrate the superiority of InfoBFR over state-of-the-art GAN-based and diffusion-based BFR methods, with around 70ms consumption, 16M trainable parameters, and nearly 85% BFR-boosting. It is promising that InfoBFR will be the first plug-and-play restorer universally employed by diverse BFR models to conquer neural degradations.
title InfoBFR: Real-World Blind Face Restoration via Information Bottleneck
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.15443