NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualization
This work addresses the problem of interactive visualization for scientists and engineers dealing with massive point cloud datasets, offering a scalable solution with high visual fidelity, though it is incremental as it builds on existing neural deferred rendering frameworks.
The paper tackles the challenge of real-time, high-fidelity visualization for large-scale scientific point clouds by introducing NAR, a neural accelerated renderer that combines a real-time pipeline with neural post-processing. It achieves competitive frame rates of over 126 fps for rendering over 350 million points, with an effective throughput exceeding 44 billion points per second using about 12 GB of memory on an RTX 2080 Ti GPU.
Exploring scientific datasets with billions of samples in real-time visualization presents a challenge - balancing high-fidelity rendering with speed. This work introduces a novel renderer - Neural Accelerated Renderer (NAR), that uses the neural deferred rendering framework to visualize large-scale scientific point cloud data. NAR augments a real-time point cloud rendering pipeline with high-quality neural post-processing, making the approach ideal for interactive visualization at scale. Specifically, we train a neural network to learn the point cloud geometry from a high-performance multi-stream rasterizer and capture the desired postprocessing effects from a conventional high-quality renderer. We demonstrate the effectiveness of NAR by visualizing complex multidimensional Lagrangian flow fields and photometric scans of a large terrain and compare the renderings against the state-of-the-art high-quality renderers. Through extensive evaluation, we demonstrate that NAR prioritizes speed and scalability while retaining high visual fidelity. We achieve competitive frame rates of $>$ 126 fps for interactive rendering of $>$ 350M points (i.e., an effective throughput of $>$ 44 billion points per second) using $\sim$12 GB of memory on RTX 2080 Ti GPU. Furthermore, we show that NAR is generalizable across different point clouds with similar visualization needs and the desired post-processing effects could be obtained with substantial high quality even at lower resolutions of the original point cloud, further reducing the memory requirements.