STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering
This work addresses the high computational cost of neural transparency rendering for real-time applications on mobile and legacy hardware.
The paper presents STAR-NT, a spatiotemporal acceleration framework that reduces rendering cost for neural order-independent transparency by exploiting spatial and temporal coherence, achieving up to 3x speedup on mobile hardware with minimal visual quality loss.
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.