提升透明物体实时渲染效率，适配移动设备
STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering
- 按屏幕局部颜色变化动态调整几何处理分辨率
- 通过深度重投影复用部分帧结果，减少计算量
- 适合移动端或老旧硬件上的高质量透明渲染
神经顺序无关透明渲染能高质量呈现重叠透明表面，但在移动和旧式硬件上，其几何处理与网络输入生成仍开销较大。本文提出一种时空加速框架，利用空间和时间一致性降低计算负担，同时保持视觉质量。空间上，采用自适应四叉树屏显分块，根据局部颜色方差动态调节几何处理分辨率；时间上，选择性帧通过基于深度的重投影复用前一帧透明结果，而非完全重渲染。两项优化协同作用，显著降低渲染成本，并可无缝集成至现有实时渲染管线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。