LoopLUT：用于实时4K图像增强的渐进式区域细化三维查找表
LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement
浏览论文内容
中文总结 AI 辅助
LoopLUT提出区域级联3D LUT，通过渐进式细化在固定低分辨率决策，实现4K实时图像增强，PSNR最高提升2.81dB，并泛化至水下场景。
中文摘要 AI 辅助
4K图像的颜色增强必须在紧凑的计算预算下达到质量目标。三维查找表（3D LUT）主导实时增强，因为它们在低分辨率下决策，并在全分辨率下进行逐像素查找。然而，单一的全局LUT在空间上是不变的，因此曝光不足的阴影区域和曝光良好的区域若具有相同的像素值，将获得相同的校正。空间异质的需求无法通过这种映射来表达。我们提出LoopLUT，一种区域级联的3D LUT，具有渐进式细化功能。全局LUT执行整体校正，随后进行K-1次循环迭代。在每次迭代中，门控头在低分辨率下预测仍需要校正的区域，然后仅根据该区域的色彩统计构建残差LUT。级联门控形成单位划分，因此输出是K个查找结果的逐像素凸组合。融合因此由门控本身执行，无需单独的融合模块，也不会在轮次间累积插值误差。决策阶段在固定的256x256分辨率下运行，与输出分辨率无关，因此4K图像仅需K次纯查找。在四个基准上的大量实验表明，LoopLUT在保持4K实时吞吐量的同时，相比最强先验方法将PSNR提升了高达2.81 dB。相同的分解也很好地泛化到水下增强数据集。
英文摘要
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.
发表机构
- Universiti Sains Malaysia（马来西亚理科大学）
- National University of Defense Technology（国防科技大学）
- Sun Yat-sen University（中山大学）
- Shandong Normal University（山东师范大学）
- Shandong University of Finance and Economics（山东财经大学）
机构由 AI 辅助整理，请以论文原文为准。
