Saved in:
Bibliographic Details
Main Authors: Joshi, Parisha, Dhillon, Daljit Singh J.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.22679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929568441434112
author Joshi, Parisha
Dhillon, Daljit Singh J.
author_facet Joshi, Parisha
Dhillon, Daljit Singh J.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22679
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Practical and Accurate Reconstruction of an Illuminant's Spectral Power Distribution for Inverse Rendering Pipelines
Joshi, Parisha
Dhillon, Daljit Singh J.
Computer Vision and Pattern Recognition
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.
title Practical and Accurate Reconstruction of an Illuminant's Spectral Power Distribution for Inverse Rendering Pipelines
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.22679