Neural Moment Transparency
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
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.
Description
CCS Concepts: Computing methodologies → Neural networks; Rasterization; Visibility
@inproceedings{10.2312:egs.20241029,
booktitle = {Eurographics 2024 - Short Papers},
editor = {Hu, Ruizhen and Charalambous, Panayiotis},
title = {{Neural Moment Transparency}},
author = {Tsopouridis, Grigoris and Vasilakis, Andreas Alexandros and Fudos, Ioannis},
year = {2024},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-237-0},
DOI = {10.2312/egs.20241029}
}