Practical and Accurate Reconstruction of an Illuminant's Spectral Power Distribution for Inverse Rendering Pipelines
This work addresses the need for affordable and accurate SPD reconstruction in photo-realistic rendering for virtual reality applications, representing an incremental improvement over existing costly spectrometer-based methods.
The paper tackles the problem of reconstructing an illuminant's spectral power distribution (SPD) for inverse rendering pipelines by proposing a low-cost method using a diffractive CD-ROM and machine learning, achieving accurate results as demonstrated through simulations and real-world examples, particularly in spectral rendering of iridescent materials.
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.