Learning Fast 3D Gaussian Splatting Rendering using Continuous Level of Detail

Abstract
3D Gaussian splatting (3DGS) has shown potential for rendering photorealistic 3D scenes in real-time. Unfortunately, rendering these scenes on less powerful hardware is still a challenge, especially with high-resolution displays. We introduce a continuous level of detail (CLOD) algorithm and demonstrate how our method can improve performance while preserving as much quality as possible. Our approach learns to order splats based on importance and optimize them such that a representative and realistic scene can be rendered for an arbitrary splat count. Our method does not require any additional memory or rendering overhead and works with existing 3DGS renderers. We also demonstrate the flexibility of our CLOD method by extending it with distance-based LOD selection, foveated rendering, and budget-based rendering.
Description

CCS Concepts: Computing methodologies → Rendering; Rasterization; Point-based models

        
@article{
10.1111:cgf.70069
, journal = {Computer Graphics Forum}, title = {{
Learning Fast 3D Gaussian Splatting Rendering using Continuous Level of Detail
}}, author = {
Milef, Nicholas
and
Seyb, Dario
and
Keeler, Todd
and
Nguyen-Phuoc, Thu
and
Bozic, Aljaz
and
Kondguli, Sushant
and
Marshall, Carl
}, year = {
2025
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.70069
} }
Citation