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.
@article{arxiv.2307.10135,
title = {A Hierarchical Architecture for Neural Materials},
author = {Bowen Xue and Shuang Zhao and Henrik Wann Jensen and Zahra Montazeri},
journal= {arXiv preprint arXiv:2307.10135},
year = {2024}
}