用不到0.25MB的模型编码512个3D色彩查找表，精度损失极小。
Efficient Neural Network Encoding for 3D Color Lookup Tables
- 设计轻量神经网络，将数百个3D LUT压缩为单一紧凑表示。
- 重建512个LUT时整体色差ΔE_M ≤ 2.0，自然图像上可降至≤1.0。
- 支持可逆编码，适合需要反向调色的应用场景。
3D颜色查找表（LUT）通过映射输入RGB值到特定输出RGB值，实现精准的色彩调控，广泛应用于视频编辑、相机处理、滤镜、计算机图形及显示色彩处理。尽管单个LUT内存开销不高，但软件与设备需存储数十至数百个LUT，总大小可能超过100MB。本文提出一种神经网络架构，可将数百个LUT压缩为仅0.25MB以下的紧凑表示。该模型能重建512个LUT，全色域范围内平均色差ΔE_M ≤ 2.0；通过加权颜色，自然图像上的色差可进一步降低至ΔE_M ≤ 1.0。此外，对网络结构稍作修改即可实现双射编码，生成可逆的LUT，支持反向色彩处理。代码已公开于https://github.com/vahidzee/ennelut。
原文摘要 · Abstract (English)
3D color lookup tables (LUTs) enable precise color manipulation by mapping input RGB values to specific output RGB values. 3D LUTs are instrumental in various applications, including video editing, in-camera processing, photographic filters, computer graphics, and color processing for displays. While an individual LUT does not incur a high memory overhead, software and devices may need to store dozens to hundreds of LUTs that can take over 100 MB. This work aims to develop a neural network architecture that can encode hundreds of LUTs in a single compact representation. To this end, we propose a model with a memory footprint of less than 0.25 MB that can reconstruct 512 LUTs with only minor color distortion ($\barΔE_M$ $\leq$ 2.0) over the entire color gamut. We also show that our network can weight colors to provide further quality gains on natural image colors ($\barΔ{E}_M$ $\leq$ 1.0). Finally, we show that minor modifications to the network architecture enable a bijective encoding that produces LUTs that are invertible, allowing for reverse color processing. Our code is available at https://github.com/vahidzee/ennelut.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。