GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation

2026-05-19

AI Summary

This work addresses the limitations of traditional 3D lookup tables (LUTs), which face a trade-off between memory consumption and representational capacity due to fixed-resolution grids, as well as the lack of interpretability and local editability in existing implicit neural approaches. The authors propose Gaussian LUT (GLUT), the first method to model continuous color transformations using learnable 3D Gaussian primitives, yielding an explicit, compact, and differentiable color mapping representation. By abandoning discrete grids, GLUT enables intuitive local region editing and leverages a conditional generative network to unify multi-style LUT modeling with smooth interpolation. Experiments demonstrate that GLUT surpasses current neural LUT methods in both mapping accuracy and efficiency while significantly enhancing interpretability and interactive editing capabilities.

Abstract

3D Lookup Tables (3D LUTs) are widely used for color mapping, but their grid-based representation requires discretizing the RGB space, leading to a capacity-memory trade-off that becomes prohibitive when storing large numbers of LUTs. Recent approaches adopt implicit neural representations to improve scalability, yet their black-box nature limits interpretability and hinders intuitive, localized editing. In this paper, we propose Gaussian LUT (GLUT), a continuous and explicit color representation that models color transformations using a set of learnable 3D Gaussian primitives. By avoiding fixed-resolution grids, GLUT achieves flexible representational capacity while maintaining a compact memory footprint. Its explicit, spatially localized formulation further enables both accurate modeling and interpretability. Building on this representation, we introduce a compact conditional generator (CGLUT) that predicts GLUT parameters for multiple LUT instances, encoding diverse color styles in a single framework to enable smooth and controllable LUT style blending. Moreover, GLUT supports efficient, user-friendly editing by allowing localized adjustments to specific color regions without global retraining. Experimental results demonstrate that our approach outperforms prior neural LUT representations in both accuracy and efficiency, while offering improved interpretability and interactive control.

Problem

• 3D LUT
• color transformation
• discretization
• interpretability
• localized editing

Innovation

• 3D Gaussian
• continuous representation
• color transformation
• interpretable editing
• conditional LUT generation