CGRG Logo
<- Back To Publications
Neural Moment Transparency

Neural Moment Transparency

Grigoris Tsopouridis, Andreas A. Vasilakis, Ioannis Fudos

Eurographics - Short Papers, 2024

We have developed a machine learning approach to efficiently compute per-fragment transmittance, using transmittance composed and accumulated with moment statistics, on a fragment shader. Our approach excels in achieving superior visual accuracy for computing order-independent transparency (OIT) in scenes with high depth complexity when compared to prior art.

View CodePublisher

Abstract

We have developed a machine learning approach to efficiently compute per-fragment transmittance, using transmittance composed and accumulated with moment statistics, on a fragment shader. Our approach excels in achieving superior visual accuracy for computing order-independent transparency (OIT) in scenes with high depth complexity when compared to prior art.

BibTeX Citation

@inproceedings{Tsopouridis2024,
booktitle = {Eurographics 2024 - Short Papers},
title = {{Neural Moment Transparency}},
author = {Tsopouridis, Grigoris and Vasilakis, Andreas Alexandros and Fudos, Ioannis},
year = {2024},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
DOI = {10.2312/egs.20241029}
}