AI RESEARCH
NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
arXiv CS.CV
•
ArXi:2511.19202v2 Announce Type: replace 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.