Abstract
Neural order-independent transparency delivers high-quality rendering of overlapping transparent surfaces, but its geometry passes and network input generation remain costly, particularly on mobile and legacy hardware. We present a spatiotemporal acceleration framework that exploits spatial and temporal coherence to reduce this overhead while preserving visual quality. Spatially, we use adaptive quadtree-based screen-space subdivision to scale geometry pass resolution according to local color variance. Temporally, selected frames reuse the previous transparency result through depth-based reprojection instead of full rendering. Together, these optimizations reduce rendering cost and integrate efficiently into existing real-time rendering pipelines. An Appendix containing supplementary material is available here: appendix. A supplementary video is available here: video.
BibTeX Citation
@inproceedings{tsopouridis2026,
author = {Grigoris Tsopouridis, Christos Georgiou-Mousses, Aris Panagiotidis, Andreas Vasilakis, David Corrigan, Tobias A. Franke, Aleksei Gorbonosov, Andrei Astapov, and Ioannis Fudos},
title = {STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering},
booktitle = {Advances in Computer Graphics - Computer Graphics International
Conference, {CGI} 2026, July 6-10, 2026, London, UK, Proceedings},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
year = {2026}
}