Metraipolis › archive › dc_9619b5ffba50
3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework — arXiv:2611.02695
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02695
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:55:07.158Z
- SHA-256 of the archived text
a933acfcde8ac7b999a5dfd967771da57d30ea79230a8b5e8aa40d5f5296b7c8- Stable URL of this page
https://metraipolis.com/documento/dc_9619b5ffba50
How to cite
3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework — arXiv:2611.02695 — arXiv (en), https://arxiv.org/abs/2611.02695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9619b5ffba50 (Metraipolis archive dc_9619b5ffba50, sha256 a933acfcde8ac7b999a5dfd967771da57d30ea79230a8b5e8aa40d5f5296b7c8)
BibTeX
@misc{dc9619b5ffba50,
title = {3L-D: A Low-Light Level Dataset from a Sensor-Agnostic, Alignment-Preserving Acquisition Framework — arXiv:2611.02695},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02695},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9619b5ffba50; sha256 a933acfcde8ac7b999a5dfd967771da57d30ea79230a8b5e8aa40d5f5296b7c8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Supervised low-light image and video enhancement has achieved remarkable progress, yet current models remain fundamentally constrained by the limitations of existing datasets. Prevailing methods typically rely on uncontrolled ambient captures, camera parameter manipulation (e.g., exposure or ISO adjustments), or neutral density filters, failing to replicate authentic night-sky near-infrared spectral content and genuine low-photon noise distributions. Furthermore, capturing dynamic paired sequences without introducing warping artifacts or sensor-specific biases remains an open challenge. In this paper, we introduce 3L-Dataset, a physically calibrated low-light image and video dataset generated using a modular, sensor-agnostic acquisition framework. Our test bench faithfully reproduces the standardized Midavaine night level scale from Level 1 (full moon, approximately 1000 mlx) down to Level 5 (overcast moonless night, approximately 0.1 mlx), spanning the visible to near-infrared spectrum across diverse realistic environments, including countryside, forest, urban, and desert scale models. Using high-precision programmable mechanical actuation, our acquisition framework guarantees sub-pixel spatial alignment across synchronized sextuplets, each composed of one reference image and five corresponding images acquired at the five standardized night levels, without post-processing image warping. We evaluate multiple representative deep learning baselines across varying night levels, revealing critical trade-offs between reconstruction fidelity, perceptual quality, and inference latency under severe photon starvation. The modular acquisition framework can be adapted to different cameras, optical systems, sensor technologies, and resolutions, enabling the dataset to be continuously expanded. 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) ; Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2611.02695 — 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 2026-11-03T18:16:53.016Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).