Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
This addresses rendering bottlenecks in 3D scene reconstruction for applications like virtual reality or gaming, representing an incremental improvement over existing 3D-GS methods.
The paper tackles the problem of inconsistent rendering speeds and excessive Gaussian primitives in 3D Gaussian splatting for large scenes by introducing Octree-GS, which uses a Level-of-Detail structured approach to achieve consistent real-time rendering while maintaining high fidelity.
The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for real-time rendering, 3D-GS encounters rendering bottlenecks in large scenes with complex details due to an excessive number of Gaussian primitives located within the viewing frustum. This limitation is particularly noticeable in zoom-out views and can lead to inconsistent rendering speeds in scenes with varying details. Moreover, it often struggles to capture the corresponding level of details at different scales with its heuristic density control operation. Inspired by the Level-of-Detail (LOD) techniques, we introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for scene representation that contributes to the final rendering results. Our model dynamically selects the appropriate level from the set of multi-resolution anchor points, ensuring consistent rendering performance with adaptive LOD adjustments while maintaining high-fidelity rendering results.