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.
@article{arxiv.2603.19187,
title = {GenMFSR: Generative Multi-Frame Image Restoration and Super-Resolution},
author = {Harshana Weligampola and Joshua Peter Ebenezer and Weidi Liu and Abhinau K. Venkataramanan and Sreenithy Chandran and Seok-Jun Lee and Hamid Rahim Sheikh},
journal= {arXiv preprint arXiv:2603.19187},
year = {2026}
}