面向时变隐式神经体积的查询高效随机体积渲染框架
A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes
- University of Utah（犹他大学）
- Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
- Vanderbilt University（范德堡大学）
- University of Arizona（亚利桑那大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对时变隐式神经体积渲染的性能挑战，提出基于delta跟踪的查询高效随机体积渲染框架，采用四阶段异构并行流水线，结合光线预算与查询剪枝，在RTX 4090上实现1024×1024分辨率下30-40 FPS及毫秒级时间步更新，支持交互式时变数据探索。
AI中文摘要：
时变隐式神经表示（INRs）为科学体积提供了紧凑表示，对于动态X射线计算机断层扫描（CT）等模态而言，它们往往是表示数据的唯一实用方式。然而，对INRs进行交互式体积渲染颇具挑战性，因为廉价的内存查找被昂贵的神经推理所取代，这阻碍了渲染性能。因此，诸如采用密集采样的光线步进之类的传统体积渲染方法往往不切实际。虽然重采样、缓存和重新训练可以缓解这种成本，但它们会损害便利性和准确性，并且对于时变数据而言变得不切实际。我们采用基于delta跟踪的查询高效随机体积渲染框架来应对这些挑战。我们的系统采用四阶段流水线，利用异构并行性，使用光线追踪核心进行遍历，使用张量核心进行批量神经评估。此外，我们提出了通过光线预算和查询剪枝减少INR查询的策略，从而提高每帧性能。使用我们的渲染器，许多时变INRs可以直接从其原始表示进行渲染。该系统在RTX 4090 GPU上以1024×1024分辨率实现约30-40 FPS，并收敛到高保真图像。此外，该系统支持对连续域进行交互式时间探索，时间步长更新耗时约1-2 ms。
英文摘要：
Time-varying implicit neural representations (INRs) provide a compact representation of scientific volumes and, for modalities such as dynamic X-ray computed tomography (CT), are often the only practical way to represent the data. However, interactive volume rendering of INRs is challenging, as cheap memory lookups are replaced by expensive neural inferences, hindering the performance. Therefore, conventional volume rendering methods such as ray marching with dense sampling are often impractical. While resampling, caching, and retraining can mitigate this cost, they compromise convenience and accuracy and become impractical for time-varying data. We tackle these challenges using a query-efficient stochastic volume rendering framework based on delta tracking. Our system employs a four-stage pipeline that exploits heterogeneous parallelism, using ray tracing cores for traversal and tensor cores for batched neural evaluation. Furthermore, we present strategies to reduce INR queries via ray budgeting and query pruning, thereby increasing per-frame performance. Using our renderer, many time-varying INRs can be rendered directly from their original representation. The system achieves ~30-40 FPS at 1024x1024 resolution on an RTX 4090 GPU and converges to high-fidelity images. Moreover, the system enables interactive temporal exploration of the continuous domain, with timestep updates taking approximately 1-2 ms.
