Neural Spectro-polarimetric Fields
Authors:
- Wonjoon JinWJWonjoon Jin
- Sunghyun ChoSCSunghyun Cho
- Seung-Hwan BaekSBSeung-Hwan Baek
Preprint
Abstract
Modeling the spatial radiance distribution of light rays in a scene has been extensively explored for applications, including view synthesis. Spectrum and polarization, the wave properties of light, are often neglected due to their integration into three RGB spectral bands and their non-perceptibility to human vision. Despite this, these properties encompass substantial material and geometric information about a scene. In this work, we propose to model spectro-polarimetric fields, the spatial Stokes-vector distribution of any light ray at an arbitrary wavelength. We present Neural Spectro-polarimetric Fields (NeSpoF), a neural representation that models the physically-valid Stokes vector at given continuous variables of position, direction, and wavelength. NeSpoF manages inherently noisy raw measurements, showcases memory efficiency, and preserves physically vital signals, factors that are crucial for representing the high-dimensional signal of a spectro-polarimetric field. To validate NeSpoF, we introduce the first multi-view hyperspectral-polarimetric image dataset, comprised of both synthetic and real-world scenes. These were captured using our compact hyperspectral-polarimetric imaging system, which has been calibrated for robustness against system imperfections. We demonstrate the capabilities of NeSpoF on diverse scenes.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- PANDORA: Polarization-Aided Neural Decomposition of Radiance2022
- Compressive full-Stokes polarization and flexible hyperspectral imaging with efficient reconstructionOptics and Lasers in Engineering, 2022
- Four-dimensional compressed spectropolarimetric imagingSignal Processing, 2022
- Tensorial Multiview Subspace Clustering for Polarimetric Hyperspectral ImagesIEEE Transactions on Geoscience and Remote Sensing, 2022
- Polarization Guided Specular Reflection SeparationIEEE Transactions on Image Processing, 2021
- Hyperspectral imaging for underwater object detectionSensor Review, 2021
- Hyperspectral polarization-compressed imaging and reconstruction with sparse basis optimized by particle swarm optimizationChemometrics and Intelligent Laboratory Systems, 2020
- Image dehazing technique based on polarimetric spectral analysisOptik, 2016
- SPICES: spectro-polarimetric imaging and characterization of exoplanetary systemsExperimental Astronomy, 2012
- Multi-View Stereo Reconstruction of Dense Shape and Complex AppearanceInternational Journal of Computer Vision, 2005