Efficient Neural Network Encoding for 3D Color Lookup Tables

Autor:	Zehtab, Vahid, Lindell, David B., Brubaker, Marcus A., Brown, Michael S.
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning Electrical Engineering and Systems Science - Image and Video Processing I.4.0 I.4.2 I.5.0 I.5.1 I.5.4 I.2.0 I.2.6 I.2.10
Druh dokumentu:	Working Paper
Popis:	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 ($\bar{\Delta}E_M$ $\leq$ 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 ($\bar{\Delta}{E}_M$ $\leq$ 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. Comment: 14 pages, 13 figures; extended version; to appear in AAAI 2025
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.15438 Zobrazit plný text záznamu View this record from Arxiv