Metraipolis › archive › dc_22e3f13fa58e
LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement — arXiv:2609.33593
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33593
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:42.483Z
- SHA-256 of the archived text
4d0cf379a3af6415f2c9669138d933aa6f1b95849ccebc0fffef4b26d83841ad- Stable URL of this page
https://metraipolis.com/documento/dc_22e3f13fa58e
How to cite
LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement — arXiv:2609.33593 — arXiv (en), https://arxiv.org/abs/2609.33593 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22e3f13fa58e (Metraipolis archive dc_22e3f13fa58e, sha256 4d0cf379a3af6415f2c9669138d933aa6f1b95849ccebc0fffef4b26d83841ad)
BibTeX
@misc{dc22e3f13fa58e,
title = {LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement — arXiv:2609.33593},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33593},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22e3f13fa58e; sha256 4d0cf379a3af6415f2c9669138d933aa6f1b95849ccebc0fffef4b26d83841ad},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33593. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Color enhancement of 4K images must meet a quality target under a tight compute budget. Three-dimensional lookup tables (3D LUTs) dominate real-time enhancement because they decide at low resolution and apply a per-pixel lookup at full resolution. A single global LUT, however, is spatially invariant, so an underexposed shadow and a well-exposed region that share a pixel value receive identical corrections. Spatially heterogeneous demands cannot be expressed by such a mapping. We propose LoopLUT, a region-cascaded 3D LUT with progressive refinement. A global LUT performs the overall correction, followed by K-1 loop iterations. In each iteration a gating head predicts at low resolution the region that still needs correction, then builds a residual LUT from the color statistics of that region alone. The cascaded gates form a partition of unity, so the output is a per-pixel convex combination of the K lookup results. Fusion is therefore performed by the gates themselves, with no separate fusion module and no interpolation error accumulating across rounds. The decision stage runs at a fixed 256x256 resolution, independent of output resolution, so a 4K image costs only K pure lookups. Extensive experiments across four benchmarks show that LoopLUT improves PSNR by up to 2.81 dB over the strongest prior method, while keeping real-time throughput at 4K. The same decomposition also generalizes well to underwater enhancement datasets. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.33593 — 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 2026-10-07T23:29:27.235Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).