发表机构
The University of Hong Kong（香港大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出Hybrid-LUT框架，通过Y通道用带像素级权重融合的多波段LUT、UV通道用轻量级滤波的非对称设计，在减少三分之二LUT存储的同时，于真实数据集上较现有LUT去噪方法提升至少0.63 dB CPSNR，实现SOTA性能。
AI 中文摘要
基于查找表（LUT）的图像去噪方法因具备高计算效率与硬件友好特性而受到日益广泛的关注。然而，现有的RGB-LUT方法需要三个相同的LUT并行处理RGB三个通道，导致片上SRAM消耗较大。一种简单的替代方案是仅在YUV颜色空间的亮度（Y）通道上应用LUT处理，以减少内存占用，但这种朴素策略会导致恢复质量下降，因为忽略色度（UV）通道会引入颜色失真与残留伪影。本研究提出了Hybrid-LUT，这是一种基于YUV的非对称通道处理框架，在统一设计中结合了LUT与滤波。具体而言，我们对Y通道应用带像素级权重融合的多波段LUT分支以恢复精细纹理，对UV通道采用轻量级滤波以保持颜色一致性。该设计相比RGB-LUT方法减少了三分之二的LUT存储量，同时维持相同的运行时吞吐量。大量实验表明，Hybrid-LUT在多个基准数据集上达到了当前最优（SOTA）性能，仅需421 KB的存储。尤其在真实世界数据集上，我们的方法超越了现有基于LUT的去噪方法至少0.63 dB的CPSNR，证明了其在资源受限边缘设备上进行图像去噪的有效性。该项目可在指定网址获取。
英文摘要
Lookup table (LUT)-based image denoising methods have attracted increasing attention due to their high efficiency and hardware-friendly properties. However, existing RGB-LUT approaches require three identical LUTs to process RGB channels in parallel, resulting in large on-chip SRAM consumption. A simple alternative is to apply LUT processing only to the luminance (Y) channel in the YUV color space to reduce memory usage. However, this naive strategy leads to degraded restoration quality, since ignoring the chrominance (UV) channels introduces color distortion and residual artifacts. In this work, we propose Hybrid-LUT, a YUV-based asymmetric channel-processing framework that combines LUT and filtering in a unified design. Specifically, a multi-band LUT branch with pixel-level weight fusion is applied to the Y channel to recover fine textures, while lightweight filtering is used for the UV channels to maintain color consistency. This design reduces LUT storage by two-thirds compared with RGB-LUT methods while maintaining the same runtime throughput. Extensive experiments show that Hybrid-LUT achieves state-of-the-art (SOTA) performance across multiple benchmarks with only 421 KB of storage. In particular, our method surpasses existing LUT-based denoising approaches by at least 0.63 dB CPSNR on real-world datasets, demonstrating its effectiveness for image denoising on resource-constrained edge devices. The project is available at https://github.com/Ai-ZL/Hybrid-LUT .
CommentsAccepted by ECCV2026
