$\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| 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 |