Practical and Accurate Reconstruction of an Illuminant's Spectral Power Distribution for Inverse Rendering Pipelines

TL;DR

This paper introduces a low-cost, machine learning-based method using a CD-ROM to accurately reconstruct the spectral power distribution of uniform illuminants, enhancing spectral rendering in inverse rendering pipelines.

Contribution

A novel, inexpensive technique for capturing illuminant SPDs without spectrometers, utilizing a diffractive CD-ROM and machine learning for improved spectral rendering.

Findings

Effective in reconstructing SPDs of spotlights in simulations

Works well with real-world examples of uniform illuminants

Improves spectral rendering of iridescent materials

Abstract

Inverse rendering pipelines are gaining prominence in realizing photo-realistic reconstruction of real-world objects for emulating them in virtual reality scenes. Apart from material reflectances, spectral rendering and in-scene illuminants' spectral power distributions (SPDs) play important roles in producing photo-realistic images. We present a simple, low-cost technique to capture and reconstruct the SPD of uniform illuminants. Instead of requiring a costly spectrometer for such measurements, our method uses a diffractive compact disk (CD-ROM) and a machine learning approach for accurate estimation. We show our method to work well with spotlights under simulations and few real-world examples. Presented results clearly demonstrate the reliability of our approach through quantitative and qualitative evaluations, especially in spectral rendering of iridescent materials.