Metraipolis › archive › dc_39616724ab3e

PRIN: A Perceptual-Structural Retinex-Inspired Network for Low-Light Image Enhancement — arXiv:2610.41338

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41338
License (as archived)
CC0-1.0
Archived
2026-11-03T08:22:01.788Z
SHA-256 of the archived text
6bb57980d61b9e8a39e23e77e2ac9309762691dbe6505e3d2698f4e35c846944
Stable URL of this page
https://metraipolis.com/documento/dc_39616724ab3e

How to cite

PRIN: A Perceptual-Structural Retinex-Inspired Network for Low-Light Image Enhancement — arXiv:2610.41338 — arXiv (en), https://arxiv.org/abs/2610.41338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39616724ab3e (Metraipolis archive dc_39616724ab3e, sha256 6bb57980d61b9e8a39e23e77e2ac9309762691dbe6505e3d2698f4e35c846944)
BibTeX
@misc{dc39616724ab3e,
  title = {PRIN: A Perceptual-Structural Retinex-Inspired Network for Low-Light Image Enhancement — arXiv:2610.41338},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41338},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39616724ab3e; sha256 6bb57980d61b9e8a39e23e77e2ac9309762691dbe6505e3d2698f4e35c846944},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Low-light image enhancement (LLIE) focuses not only on visibility recovery but also on preserving structurally meaningful content and perceptual naturalness. Existing learning-based methods may achieve favorable pixel-wise fidelity while still producing over-smoothed textures, color deviations, or spatially incoherent illumination. Retinex-inspired methods provide interpretable decomposition into reflectance and illumination components, however, the asymmetric restoration roles of these components are rarely encoded through branch-specific frequency-domain refinement. To address this issue, we propose a Perceptual-Structural Retinex-Inspired Network (PRIN), which integrates Retinex priors with restoration-role-aware enhancement. PRIN employs a shared encoder and asymmetric decoders to estimate reflectance and illumination components. The reflectance branch performs attention-guided and edge-aware wavelet refinement to preserve textures and boundaries, whereas the illumination branch promotes spatially coherent brightness adjustment. After the recomposition of reflectance and illumination branches, a curve-based post-composition enhancement head calibrates residual tone and exposure deviations. Experiments on LOL-v1, LOL-v2-Syn, and LOL-v2-Real show that the proposed network ties for the best structural similarity index (SSIM) and obtains the second-lowest learned perceptual image patch similarity (LPIPS) on LOL-v1, achieves the best SSIM and LPIPS on LOL-v2-Syn, and obtains the highest peak signal-to-noise ratio (PSNR) and the second-lowest LPIPS on LOL-v2-Real.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41338 — 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 2026-11-03T08:06:38.866Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).