Efficient Neural Network Encoding for 3D Color Lookup Tables

TL;DR

This paper introduces a compact neural network that efficiently encodes hundreds of 3D color LUTs, enabling high-fidelity color mapping with minimal memory usage and invertibility for reverse processing.

Contribution

A novel neural network architecture that encodes multiple 3D LUTs in a small, memory-efficient model with invertible capabilities for reverse color processing.

Findings

Encodes 512 LUTs with less than 0.25 MB memory

Achieves minor color distortion ($ar{ ext{E}}_M \

) 2.0) across the color gamut,

Abstract

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.