Metraipolis › archive › dc_244ec8ba2d65

What Does LOL Measure? Hidden Label Shifts in Low-Light Enhancement Benchmarks — arXiv:2610.38121

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38121
License (as archived)
CC0-1.0
Archived
2026-11-01T02:26:54.811Z
SHA-256 of the archived text
cc3a7d1157d447f7ae08daa65ccfa060afa8a9d507d0ec9377af368ca6be42fa
Stable URL of this page
https://metraipolis.com/documento/dc_244ec8ba2d65

How to cite

What Does LOL Measure? Hidden Label Shifts in Low-Light Enhancement Benchmarks — arXiv:2610.38121 — arXiv (en), https://arxiv.org/abs/2610.38121 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_244ec8ba2d65 (Metraipolis archive dc_244ec8ba2d65, sha256 cc3a7d1157d447f7ae08daa65ccfa060afa8a9d507d0ec9377af368ca6be42fa)
BibTeX
@misc{dc244ec8ba2d65,
  title = {What Does LOL Measure? Hidden Label Shifts in Low-Light Enhancement Benchmarks — arXiv:2610.38121},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38121},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_244ec8ba2d65; sha256 cc3a7d1157d447f7ae08daa65ccfa060afa8a9d507d0ec9377af368ca6be42fa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38121. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LOL-v1 and LOLv2-Real are the standard benchmarks for supervised low-light image enhancement, and several leading methods ship hand-set test-time adjustments with their evaluation scripts. We audit both benchmarks with 18 public checkpoints of eight methods under one metric implementation that reproduces every published number to within 0.09 dB, and find that their test labels differ from their training labels. (i) The 15 LOL-v1 test labels are rendered differently: the same captures appear in LOLv2 with labels of identical luminance but 1.48x lower saturation, and LOL-v1's own training labels match the LOLv2 rendering; we confirm this on the official release. (ii) The LOLv2-Real test set is the contiguous block of images 690-789, whose labels are 14% darker than the training labels (Cliff's delta = -0.45, p < 1e-12) with no comparable shift in the input statistics we examined; methods trained without any labels score up to 5.5 dB higher on test than on train. (iii) All 15 LOL-v1 test inputs reappear in LOLv2-Real, 12 in its training set. The released test-time settings are consistent with compensating for these shifts. Separating what can be calibrated on training data from what only test-set tuning finds, the test-only residual has median 0.00 dB on LOLv2-Syn, which has no shift, but 0.37 dB on LOL-v1 and 0.92 dB on LOLv2-Real (up to 3.9 dB). Under the shift, test-set checkpoint selection inflates a from-scratch model by 0.9-2.0 dB, and removing the released settings changes which method ranks first. We give concrete reporting recommendations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2610.38121 — 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 2026-11-01T02:12:44.247Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).