Pigmento: Pigment-Based Image Analysis and Editing

TL;DR

Pigmento introduces a novel method to analyze and edit images based on pigment decomposition, enabling more realistic and versatile digital editing by modeling images as mixtures of physical pigments.

Contribution

The paper presents an efficient algorithm for recovering pigment structures from RGB images, allowing for pigment-based image editing operations that produce plausible and novel visual effects.

Findings

Successfully recovers pigments close to ground truth in some cases

Produces plausible pigment decompositions in all tested images

Enables new image editing techniques in pigment space

Abstract

The colorful appearance of a physical painting is determined by the distribution of paint pigments across the canvas, which we model as a per-pixel mixture of a small number of pigments with multispectral absorption and scattering coefficients. We present an algorithm to efficiently recover this structure from an RGB image, yielding a plausible set of pigments and a low RGB reconstruction error. We show that under certain circumstances we are able to recover pigments that are close to ground truth, while in all cases our results are always plausible. Using our decomposition, we repose standard digital image editing operations as operations in pigment space rather than RGB, with interestingly novel results. We demonstrate tonal adjustments, selection masking, cut-copy-paste, recoloring, palette summarization, and edge enhancement.