A Hierarchical Architecture for Neural Materials

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,...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Bowen, Xue, Zhao, Shuang, Jensen, Henrik Wann, Montazeri, Zahra
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 24.04.2024
Subjects
Materials handling
Model accuracy
Neural networks
Reflectance
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422