NeISF++ generalizes the dielectric-only NeISF polarized inverse renderer to conductors by adding a complex-refractive-index Fresnel term and a DoLP-based geometry initialization, improving metal and dielectric reconstruction.
Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this work, we propose a novel learning-based method to jointly estimate the shape and subsurface scattering (SSS) parameters of translucent objects by utilizing polarization cues. Although polarization cues have been used in various applications, such as shape from polarization (SfP), BRDF estimation, and reflection removal, their application in SSS estimation has not yet been explored. Our observations indicate that the SSS affects not only the light intensity but also the polarization signal. Hence, the polarization signal can provide additional cues for SSS estimation. We also introduce the first large-scale synthetic dataset of polarized translucent objects for training our model. Our method outperforms several baselines from the SfP and inverse rendering realms on both synthetic and real data, as demonstrated by qualitative and quantitative results.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectrics
NeISF++ generalizes the dielectric-only NeISF polarized inverse renderer to conductors by adding a complex-refractive-index Fresnel term and a DoLP-based geometry initialization, improving metal and dielectric reconstruction.