Metraipolis › archive › dc_092ab6574516

MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration — arXiv:2609.25331

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25331
License (as archived)
CC0-1.0
Archived
2026-10-08T16:39:04.884Z
SHA-256 of the archived text
f14f5d8a8d9c12c6aca038a0de0cad38d157fdefd837f875c85aada564d66707
Stable URL of this page
https://metraipolis.com/documento/dc_092ab6574516

How to cite

MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration — arXiv:2609.25331 — arXiv (en), https://arxiv.org/abs/2609.25331 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_092ab6574516 (Metraipolis archive dc_092ab6574516, sha256 f14f5d8a8d9c12c6aca038a0de0cad38d157fdefd837f875c85aada564d66707)
BibTeX
@misc{dc092ab6574516,
  title = {MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration — arXiv:2609.25331},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25331},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_092ab6574516; sha256 f14f5d8a8d9c12c6aca038a0de0cad38d157fdefd837f875c85aada564d66707},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25331. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surveillance, au- tonomous navigation, remote sensing, and inspection in poorly lit industrial environments. Most LLIE methods rely on output- level reconstruction losses that supervise only the final restored image, leaving the intermediate feature recovery process weakly constrained. This paper proposes MirrorDistill, an illumination- aware latent distillation framework that links the low-light and clean domains through feature mirroring. During training, a shared encoder and an exponential-moving-average teacher decoder process the clean reference image to generate clean- domain latent targets. These targets supervise the low-light student at two levels: raw encoder features and standardized multi-scale decoder projections. The alignment is applied layer by layer, while a proposed illumination-aware weighting scheme gives greater emphasis to underexposed regions. The teacher and reference branches are used only during training, so inference requires only the lightweight student encoder-decoder and in- troduces no teacher-side computational cost. Under evaluation on the standard LOL benchmarks, MirrorDistill outperforms the state-of-the-art methods on the real-captured LOL-v2-Real set, while having the lowest compute complexity (GMACs) and while remaining competitive on the LOL-v1 and LOL-v2-Synthetic datasets. Ablation studies further show the contributions of the encoder mirror, decoder mirror, and illumination-aware weighting. Finally, we release our code as open-source for the benefit of future research.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.25331 — 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 2026-10-08T15:56:18.083Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).