RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mosleh, Ali, Ali, Faraz, Zhang, Fengjia, Tsogkas, Stavros, Lee, Junyong, Levinshtein, Alex, Brown, Michael S.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910051510255616
author Mosleh, Ali
Ali, Faraz
Zhang, Fengjia
Tsogkas, Stavros
Lee, Junyong
Levinshtein, Alex
Brown, Michael S.
author_facet Mosleh, Ali
Ali, Faraz
Zhang, Fengjia
Tsogkas, Stavros
Lee, Junyong
Levinshtein, Alex
Brown, Michael S.
contents Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via ``unprocessing'' pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image RAW-to-RGB SR model and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12493
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution
Mosleh, Ali
Ali, Faraz
Zhang, Fengjia
Tsogkas, Stavros
Lee, Junyong
Levinshtein, Alex
Brown, Michael S.
Computer Vision and Pattern Recognition
Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data generation via ``unprocessing'' pipelines offers a potential solution by simulating the degradations that transform high-resolution (HR) images into their low-resolution (LR) counterparts. However, these pipelines can introduce domain gaps due to incomplete or unrealistic degradation modeling. In this paper, we demonstrate that principled and carefully designed degradation modeling can enhance SR performance in real-world conditions. Instead of relying on generic priors for camera blur and noise, we model device-specific degradations through calibration and unprocess publicly available rendered images into the RAW domain of different smartphones. Using these image pairs, we train a single-image RAW-to-RGB SR model and evaluate it on real data from a held-out device. Our experiments show that accurate degradation modeling leads to noticeable improvements, with our SR model outperforming baselines trained on large pools of arbitrarily chosen degradations.
title RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.12493