[
    {
        "id": "osp-24690",
        "type": "article-journal",
        "title": "LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement",
        "author": [
            {
                "family": "Ye",
                "given": "Yang"
            },
            {
                "family": "Ma",
                "given": "Jiajun"
            },
            {
                "family": "Wu",
                "given": "Chen"
            },
            {
                "family": "Wang",
                "given": "Wei"
            },
            {
                "family": "Lu",
                "given": "Dianjie"
            },
            {
                "family": "Zhang",
                "given": "Guijuan"
            },
            {
                "family": "Fan",
                "given": "Linwei"
            },
            {
                "family": "Zheng",
                "given": "Zhuoran"
            }
        ],
        "URL": "https://omanscience.com/en/articles/looplut-3d-lookup-tables-with-progressive-region-refinement-for-real-time-4k-image-enhancement",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "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."
    }
]