Metraipolis › archive › dc_33338db48e0d
CHROMA-MILL: Joint Low-Light Enhancement and White Balance under Colored Illumination — arXiv:2611.04092
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04092
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:56:09.071Z
- SHA-256 of the archived text
742838d2503a3fc6497ab0364bb9127e5a03cd4357b27b31db490e219c32dea8- Stable URL of this page
https://metraipolis.com/documento/dc_33338db48e0d
How to cite
CHROMA-MILL: Joint Low-Light Enhancement and White Balance under Colored Illumination — arXiv:2611.04092 — arXiv (en), https://arxiv.org/abs/2611.04092 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33338db48e0d (Metraipolis archive dc_33338db48e0d, sha256 742838d2503a3fc6497ab0364bb9127e5a03cd4357b27b31db490e219c32dea8)
BibTeX
@misc{dc33338db48e0d,
title = {CHROMA-MILL: Joint Low-Light Enhancement and White Balance under Colored Illumination — arXiv:2611.04092},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04092},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33338db48e0d; sha256 742838d2503a3fc6497ab0364bb9127e5a03cd4357b27b31db490e219c32dea8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04092. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Capturing an image in a low-light environment produces a weak, noisy sensor signal. Low-light image enhancement (LLIE) aims to restore it. Auto white balance (AWB) is also required for every image, and the same noisy signal degrades its ability to infer the scene illuminant. LLIE is typically performed first, followed by AWB, but this strategy remains largely unexamined because existing low-light datasets span a narrow range of illuminants and lack illuminant ground truth for evaluating AWB. We address this with CHROMA-MILL, a RAW dataset of 50 scenes captured with a DSLR and smartphone under four calibrated illuminants at eleven intensity levels. Because light is additive, we blend these captures in the linear RAW domain to synthesize physically valid illuminant mixtures with exact chromaticity ground truth. Benchmarking on this data, we find joint correction is best, and introduce CTI-Retinexformer, which supervises an illumination map, a chromaticity prediction, and an illumination-invariant scene embedding, outperforming the best cascade by 0.7 dB PSNR$_L$ and 1.1 $\Delta E_{00}$.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.04092 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:33:47.103Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).