Neural networks have shown great potential in compressing volumetric data for scientific visualization. However, due to the high cost of training and inference, such volumetric neural representations have thus far only been applied to offline data processing and non-interactive rendering. In this paper, we demonstrate that by simultaneously leveraging modern GPU tensor cores, a native CUDA neural network framework, and online training, we can achieve high-performance and high-fidelity interactive ray tracing using volumetric neural representations. Additionally, our method is fully generalizable and can adapt to time-varying datasets on-the-fly. We present three strategies for online training with each leveraging a different combination of the GPU, the CPU, and out-of-core-streaming techniques. We also develop three rendering implementations that allow interactive ray tracing to be coupled with real-time volume decoding, sample streaming, and in-shader neural network inference. We demonstrate that our volumetric neural representations can scale up to terascale for regular-grid volume visualization, and can easily support irregular data structures such as OpenVDB, unstructured, AMR, and particle volume data.
翻译:神经网络在压缩体积数据以进行科学直观化方面显示出巨大的潜力,然而,由于培训和推断费用高昂,这种体积神经表征迄今只应用于离线数据处理和非互动造影。在本文件中,我们证明,通过同时利用现代GPU 高温核心、本地CUDA神经网络框架和在线培训,我们能够通过体积内神经显示实现高性能和高纤维互动射线追踪。此外,我们的体积神经表征完全可以普及,可以适应在飞行时变数据集。我们提出了三种在线培训战略,每种方法都利用GPU、CPU和核心流外技术的不同组合。我们还开发了三种实施方法,使交互式射线追踪能够与实时量解码、样本流和电离神经网络的推断相结合。我们证明,我们的体积神经表能可以扩大成固定电网体积可视化的体积成成形,并且可以很容易地支持不规则的数据结构,如OpenVDO、ODB、ODO、ODB、ODA和ODRA等非数据结构。