$\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rothschild, Nate, Kimhi, Moshe, Mendelson, Avi, Baskin, Chaim
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908733425057792
author Rothschild, Nate
Kimhi, Moshe
Mendelson, Avi
Baskin, Chaim
author_facet Rothschild, Nate
Kimhi, Moshe
Mendelson, Avi
Baskin, Chaim
contents Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing pipeline irreversibly mixes colors, clips dynamic range, and blurs fine detail. This paper uses the rain degradation problem as a use case to show that these losses are avoidable, and demonstrates that learning directly on raw Bayer mosaics yields superior reconstructions. To substantiate the claim, we (i) evaluate post-ISP and Bayer reconstruction pipelines, (ii) curate Raw-Rain, the first public benchmark of real rainy scenes captured in both 12-bit Bayer and bit-depth-matched sRGB, and (iii) introduce Information Conservation Score (ICS), a color-invariant metric that aligns more closely with human opinion than PSNR or SSIM. On the test split, our raw-domain model improves sRGB results by up to +0.99 dB PSNR and +1.2% ICS, while running faster with half of the GFLOPs. The results advocate an ISP-last paradigm for low-level vision and open the door to end-to-end learnable camera pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24022
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle $\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
Rothschild, Nate
Kimhi, Moshe
Mendelson, Avi
Baskin, Chaim
Computer Vision and Pattern Recognition
Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing pipeline irreversibly mixes colors, clips dynamic range, and blurs fine detail. This paper uses the rain degradation problem as a use case to show that these losses are avoidable, and demonstrates that learning directly on raw Bayer mosaics yields superior reconstructions. To substantiate the claim, we (i) evaluate post-ISP and Bayer reconstruction pipelines, (ii) curate Raw-Rain, the first public benchmark of real rainy scenes captured in both 12-bit Bayer and bit-depth-matched sRGB, and (iii) introduce Information Conservation Score (ICS), a color-invariant metric that aligns more closely with human opinion than PSNR or SSIM. On the test split, our raw-domain model improves sRGB results by up to +0.99 dB PSNR and +1.2% ICS, while running faster with half of the GFLOPs. The results advocate an ISP-last paradigm for low-level vision and open the door to end-to-end learnable camera pipelines.
title $\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.24022