English(EN) STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering

STAR-NT 框架加速实时神经透明渲染

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-15 14:07

研究人员开发了 STAR-NT，一个旨在加速实时神经透明渲染的新型框架。该方法解决了渲染重叠透明表面所带来的高计算成本问题，尤其是在性能较低的硬件上。通过采用基于自适应四叉树的屏幕空间细分以及通过基于深度的重投影进行时间帧重用，STAR-NT 在保持视觉保真度的同时显著降低了渲染开销。 AI

排序理由该集群包含一篇发表在 arXiv 上的研究论文，详细介绍了一个新的技术框架。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Grigoris Tsopouridis, Christos Georgiou-Mousses, Aris Panagiotidis, Andreas Vasilakis, David Corrigan, Tobias A. Franke, Aleksei Gorbonosov, Andrei Astapov, Ioannis Fudos · 2026-06-16 04:00

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

arXiv:2606.16747v1 Announce Type: cross 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 …
arXiv cs.LG TIER_1 English(EN) · Ioannis Fudos · 2026-06-15 14:07

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

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 explo…