Metraipolis › archive › dc_db778f12ace4
ILLRAW: Illumination-Aware RAW Object Detection — arXiv:2611.02995
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02995
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:42:43.791Z
- SHA-256 of the archived text
17eb7dceec8f4e8a7344b579a58975dc280dac881289d9940991feb237edaac9- Stable URL of this page
https://metraipolis.com/documento/dc_db778f12ace4
How to cite
ILLRAW: Illumination-Aware RAW Object Detection — arXiv:2611.02995 — arXiv (en), https://arxiv.org/abs/2611.02995 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db778f12ace4 (Metraipolis archive dc_db778f12ace4, sha256 17eb7dceec8f4e8a7344b579a58975dc280dac881289d9940991feb237edaac9)
BibTeX
@misc{dcdb778f12ace4,
title = {ILLRAW: Illumination-Aware RAW Object Detection — arXiv:2611.02995},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02995},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db778f12ace4; sha256 17eb7dceec8f4e8a7344b579a58975dc280dac881289d9940991feb237edaac9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02995. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing RAW-based detectors typically introduce learnable ISP modules to convert RAW inputs into sRGB-like formats to fit off-the-shelf detectors. However, this RAW-to-sRGB paradigm decouples representation learning from the downstream detection task. Crucially, it forces the network to inherit human-centric visual priors while discarding intrinsic RAW advantages, such as linear sensor responses and high-bit-depth, minimally processed scene cues. In this paper, we propose \textbf{ILLRAW}, an \textbf{ILL}umination-aware end-to-end \textbf{RAW} object detection framework. Instead of reconstructing visually plausible sRGB images, ILLRAW directly learns detection-oriented RAW features through a lightweight feature adapter inserted at the input stage of existing detectors. ILLRAW estimates an illumination mask and introduces channel-sensitive embeddings to model Bayer-channel responses. These features are fused by an illumination attention fusion module. Experiments show clear improvements on the diverse AODRaw benchmark and competitive performance on LOD and PascalRAW, with particularly strong results under dark exposure.
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/2611.02995 — 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 2026-11-03T11:06:37.607Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).