SimLOD: Simultaneous LOD Generation and Rendering

TL;DR

SimLOD enables real-time, incremental level-of-detail generation and rendering of large point clouds by streaming data from SSDs and updating octree structures on the GPU, allowing immediate visualization without preprocessing.

Contribution

This work introduces a GPU-based, incremental LOD construction method that streams data from SSDs and updates octree structures in real time, enabling immediate visualization of large point clouds.

Findings

Achieves up to 580 million points per second streaming rate.

Inserts several million points per frame into the octree.

Maintains real-time rendering with 1-2 ms update times.

Abstract

About: We propose an incremental LOD generation approach for point clouds that allows us to simultaneously load points from disk, update an octree-based level-of-detail representation, and render the intermediate results in real time while additional points are still being loaded from disk. LOD construction and rendering are both implemented in CUDA and share the GPU's processing power, but each incremental update is lightweight enough to leave enough time to maintain real-time frame rates. Background: LOD construction is typically implemented as a preprocessing step that requires users to wait before they are able to view the results in real time. This approach allows users to view intermediate results right away. Results: Our approach is able to stream points from an SSD and update the octree on the GPU at rates of up to 580 million points per second (~9.3GB/s from a PCIe 5.0 SSD) on an RTX 4090. Depending on the data set, our approach spends an average of about 1 to 2 ms to incrementally insert 1 million points into the octree, allowing us to insert several million points per frame into the LOD structure and render the intermediate results within the same frame. Discussion/Limitations: We aim to provide near-instant, real-time visualization of large data sets without preprocessing. Out-of-core processing of arbitrarily large data sets and color-filtering for higher-quality LODs are subject to future work.