ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2412.15438
89
0

Efficient Neural Network Encoding for 3D Color Lookup Tables

19 December 2024
Vahid Zehtab
David B. Lindell
Marcus A. Brubaker
Michael S. Brown
    3DV
    VOS
ArXivPDFHTML
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 (ΔˉEM\bar{\Delta}E_MΔˉEM​ ≤\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 (ΔˉEM\bar{\Delta}{E}_MΔˉEM​ ≤\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.

View on arXiv
Comments on this paper