Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting

About

3D Gaussian Splatting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of another highly effective technique: occlusion culling. We address this limitation by proposing a novel method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP across instances of an asset in a scene. By querying it for Gaussians within the viewing frustum prior to rasterization, our method can discard occluded primitives during rendering. Leveraging Tensor Cores for efficient computation, we integrate these neural queries directly into a novel instanced software rasterizer. Our approach outperforms the current state of the art for composed scenes in terms of VRAM usage and image quality, utilizing a combination of our instanced rasterizer and occlusion culling MLP, and exhibits complementary properties to existing LoD techniques.

Brent Zoomers, Florian Hahlbohm, Joni Vanherck, Lode Jorissen, Marcus Magnor, Nick Michiels• 2025

Related benchmarks

TaskDatasetResultRank
3D Scene RenderingFOREST scene
PSNR52.7
4
3D Scene RenderingCROWD scene
PSNR49.2
4
3D Scene RenderingDONUTSEA scene
PSNR64.2
4
Novel View SynthesisTEMPLES layout V3DG
PSNR45.21
4
Build-time estimationTrees
Build Time3
2
Build-time estimationMVHumanNet
Build Time4
2
Build-time estimationDonut
Build Time2
2
Showing 7 of 7 rows

Other info

Follow for update