Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kazerouni, Amirhossein, Suin, Maitreya, Aumentado-Armstrong, Tristan, Honari, Sina, Walia, Amanpreet, Mohomed, Iqbal, Derpanis, Konstantinos G., Taati, Babak, Levinshtein, Alex
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908948850802688
author Kazerouni, Amirhossein
Suin, Maitreya
Aumentado-Armstrong, Tristan
Honari, Sina
Walia, Amanpreet
Mohomed, Iqbal
Derpanis, Konstantinos G.
Taati, Babak
Levinshtein, Alex
author_facet Kazerouni, Amirhossein
Suin, Maitreya
Aumentado-Armstrong, Tristan
Honari, Sina
Walia, Amanpreet
Mohomed, Iqbal
Derpanis, Konstantinos G.
Taati, Babak
Levinshtein, Alex
contents Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods focus solely on facial regions, neglecting degradation across the full scene, including body and background, which limits practical usability. Meanwhile, full-scene restorers often ignore degradation cues entirely, leading to underdetermined predictions and visual artifacts. In this work, we propose Face2Scene, a two-stage restoration framework that leverages the face as a perceptual oracle to estimate degradation and guide the restoration of the entire image. Given a degraded image and one or more identity references, we first apply a Ref-FR model to reconstruct high-quality facial details. From the restored-degraded face pair, we extract a face-derived degradation code that captures degradation attributes (e.g., noise, blur, compression), which is then transformed into multi-scale degradation-aware tokens. These tokens condition a diffusion model to restore the full scene in a single step, including the body and background. Extensive experiments demonstrate the superior effectiveness of the proposed method compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16570
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
Kazerouni, Amirhossein
Suin, Maitreya
Aumentado-Armstrong, Tristan
Honari, Sina
Walia, Amanpreet
Mohomed, Iqbal
Derpanis, Konstantinos G.
Taati, Babak
Levinshtein, Alex
Computer Vision and Pattern Recognition
Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods focus solely on facial regions, neglecting degradation across the full scene, including body and background, which limits practical usability. Meanwhile, full-scene restorers often ignore degradation cues entirely, leading to underdetermined predictions and visual artifacts. In this work, we propose Face2Scene, a two-stage restoration framework that leverages the face as a perceptual oracle to estimate degradation and guide the restoration of the entire image. Given a degraded image and one or more identity references, we first apply a Ref-FR model to reconstruct high-quality facial details. From the restored-degraded face pair, we extract a face-derived degradation code that captures degradation attributes (e.g., noise, blur, compression), which is then transformed into multi-scale degradation-aware tokens. These tokens condition a diffusion model to restore the full scene in a single step, including the body and background. Extensive experiments demonstrate the superior effectiveness of the proposed method compared to state-of-the-art methods.
title Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.16570