ColorGradedGaussians: Palette-Based Color Grading for 3D Gaussian Splatting via View-Space Sparse Decomposition

2026-04-01

AI Summary

Existing palette-based 3D Gaussian splatting methods perform color decomposition in the original attribute space, which struggles to achieve pixel-level sparsity and precise control over color and luminance. This work proposes a view-space sparse palette shading framework that, for the first time, optimizes palette weights at the level of pixel visibility and introduces an inverse barycentric coordinate geometric loss to enforce spatial consistency and sparsity in color decomposition. The method enables professional-grade functionalities such as palette recoloring and tone curve adjustment while maintaining real-time rendering performance. It significantly enhances the accuracy and interactivity of color editing, effectively meeting the demanding requirements of high-quality color grading in 3D scenes.

Abstract

Professional color editing requires precise control over both color (hue and saturation) and lightness, ideally through separate, independent controls. We present a real-time interactive color editing framework for 3D Gaussian Splatting (3DGS) that enables palette-based recoloring, per-palette tone curves for color-aware lightness adjustment, and accurate pixel-level constraints -- capabilities unavailable in prior palette-based 3DGS methods. Existing approaches decompose colors at the primitive level, optimizing per-Gaussian palette weights before splatting. However, sparse primitive-level weights do not guarantee sparse pixel-level decompositions after alpha-blending, causing palette edits to affect unintended regions and degrading editing quality. We address this through view-space palette decomposition, splatting weights instead of colors to optimize the observable appearance of the scene. We introduce a geometric loss using inverse barycentric coordinates to enforce consistent sparsity patterns, ensuring similar colors share similar decompositions. Our approach achieves superior editing quality compared to primitive-space methods, enabling professional color grading workflows for 3DGS scenes with real-time interaction.

Problem

• Color Grading
• 3D Gaussian Splatting
• Palette-Based Editing
• Sparse Decomposition
• View-Space

Innovation

• 3D Gaussian Splatting
• palette-based color grading
• view-space decomposition
• sparse representation
• real-time editing