# STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering

arXiv: https://arxiv.org/abs/2606.16747 · HTML: https://mlsanity.com/paper/2606.16747/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 22 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 3 of 3)

- [Deep Shading: Convolutional Neural Networks for Screen-Space Shading](https://mlsanity.com/paper/1603.06078/) (2016)
- [Neural Shadow Mapping](https://mlsanity.com/paper/2301.05262/) (2023)
- [Deep and Fast Approximate Order Independent Transparency](https://mlsanity.com/paper/2305.10197/) (2023)

## Abstract (arXiv)

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.