A Hierarchical Architecture for Neural Materials
Loading...
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
Abstract
Neural reflectance models are capable of reproducing the spatially‐varying appearance of many real‐world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong shadowing effects or detailed specular highlights. In this paper, we introduce a neural appearance model that offers a new level of accuracy. Central to our model is an inception‐based core network structure that captures material appearances at multiple scales using parallel‐operating kernels and ensures multi‐stage features through specialized convolution layers. Furthermore, we encode the inputs into frequency space, introduce a gradient‐based loss, and employ it adaptive to the progress of the learning phase. We demonstrate the effectiveness of our method using a variety of synthetic and real examples.
Description
@article{10.1111:cgf.15116,
journal = {Computer Graphics Forum},
title = {{A Hierarchical Architecture for Neural Materials}},
author = {Xue, Bowen and Zhao, Shuang and Jensen, Henrik Wann and Montazeri, Zahra},
year = {2024},
publisher = {© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.},
DOI = {10.1111/cgf.15116}
}