- TL;DR: We introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for both scene geometry and rendering results. + TL;DR: 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.
- The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and excels in speed compared to NeRF-basedneural scene representations. - While demonstrating the potential for realtime 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. + 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 to the different scales with its heuristic Gaussian growing operation. - Inspired by the Level-of-details (LOD) techniques, we introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for both scene geometry and rendering results. + 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 \modelname, 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.