GenMFSR: Generative Multi-Frame Image Restoration and Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weligampola, Harshana, Ebenezer, Joshua Peter, Liu, Weidi, Venkataramanan, Abhinau K., Chandran, Sreenithy, Lee, Seok-Jun, Sheikh, Hamid Rahim
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912974569996288
author Weligampola, Harshana
Ebenezer, Joshua Peter
Liu, Weidi
Venkataramanan, Abhinau K.
Chandran, Sreenithy
Lee, Seok-Jun
Sheikh, Hamid Rahim
author_facet Weligampola, Harshana
Ebenezer, Joshua Peter
Liu, Weidi
Venkataramanan, Abhinau K.
Chandran, Sreenithy
Lee, Seok-Jun
Sheikh, Hamid Rahim
contents Camera pipelines receive raw Bayer-format frames that need to be denoised, demosaiced, and often super-resolved. Multiple frames are captured to utilize natural hand tremors and enhance resolution. Multi-frame super-resolution is therefore a fundamental problem in camera pipelines. Existing adversarial methods are constrained by the quality of ground truth. We propose GenMFSR, the first Generative Multi-Frame Raw-to-RGB Super Resolution pipeline, that incorporates image priors from foundation models to obtain sub-pixel information for camera ISP applications. GenMFSR can align multiple raw frames, unlike existing single-frame super-resolution methods, and we propose a loss term that restricts generation to high-frequency regions in the raw domain, thus preventing low-frequency artifacts.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19187
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GenMFSR: Generative Multi-Frame Image Restoration and Super-Resolution
Weligampola, Harshana
Ebenezer, Joshua Peter
Liu, Weidi
Venkataramanan, Abhinau K.
Chandran, Sreenithy
Lee, Seok-Jun
Sheikh, Hamid Rahim
Image and Video Processing
Camera pipelines receive raw Bayer-format frames that need to be denoised, demosaiced, and often super-resolved. Multiple frames are captured to utilize natural hand tremors and enhance resolution. Multi-frame super-resolution is therefore a fundamental problem in camera pipelines. Existing adversarial methods are constrained by the quality of ground truth. We propose GenMFSR, the first Generative Multi-Frame Raw-to-RGB Super Resolution pipeline, that incorporates image priors from foundation models to obtain sub-pixel information for camera ISP applications. GenMFSR can align multiple raw frames, unlike existing single-frame super-resolution methods, and we propose a loss term that restricts generation to high-frequency regions in the raw domain, thus preventing low-frequency artifacts.
title GenMFSR: Generative Multi-Frame Image Restoration and Super-Resolution
topic Image and Video Processing
url https://arxiv.org/abs/2603.19187