A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kerbl, Bernhard, Meuleman, Andréas, Kopanas, Georgios, Wimmer, Michael, Lanvin, Alexandre, Drettakis, George
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916290516484096
author Kerbl, Bernhard
Meuleman, Andréas
Kopanas, Georgios
Wimmer, Michael
Lanvin, Alexandre
Drettakis, George
author_facet Kerbl, Bernhard
Meuleman, Andréas
Kopanas, Georgios
Wimmer, Michael
Lanvin, Alexandre
Drettakis, George
contents Novel view synthesis has seen major advances in recent years, with 3D Gaussian splatting offering an excellent level of visual quality, fast training and real-time rendering. However, the resources needed for training and rendering inevitably limit the size of the captured scenes that can be represented with good visual quality. We introduce a hierarchy of 3D Gaussians that preserves visual quality for very large scenes, while offering an efficient Level-of-Detail (LOD) solution for efficient rendering of distant content with effective level selection and smooth transitions between levels.We introduce a divide-and-conquer approach that allows us to train very large scenes in independent chunks. We consolidate the chunks into a hierarchy that can be optimized to further improve visual quality of Gaussians merged into intermediate nodes. Very large captures typically have sparse coverage of the scene, presenting many challenges to the original 3D Gaussian splatting training method; we adapt and regularize training to account for these issues. We present a complete solution, that enables real-time rendering of very large scenes and can adapt to available resources thanks to our LOD method. We show results for captured scenes with up to tens of thousands of images with a simple and affordable rig, covering trajectories of up to several kilometers and lasting up to one hour. Project Page: https://repo-sam.inria.fr/fungraph/hierarchical-3d-gaussians/
format Preprint
id arxiv_https___arxiv_org_abs_2406_12080
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets
Kerbl, Bernhard
Meuleman, Andréas
Kopanas, Georgios
Wimmer, Michael
Lanvin, Alexandre
Drettakis, George
Computer Vision and Pattern Recognition
Graphics
Novel view synthesis has seen major advances in recent years, with 3D Gaussian splatting offering an excellent level of visual quality, fast training and real-time rendering. However, the resources needed for training and rendering inevitably limit the size of the captured scenes that can be represented with good visual quality. We introduce a hierarchy of 3D Gaussians that preserves visual quality for very large scenes, while offering an efficient Level-of-Detail (LOD) solution for efficient rendering of distant content with effective level selection and smooth transitions between levels.We introduce a divide-and-conquer approach that allows us to train very large scenes in independent chunks. We consolidate the chunks into a hierarchy that can be optimized to further improve visual quality of Gaussians merged into intermediate nodes. Very large captures typically have sparse coverage of the scene, presenting many challenges to the original 3D Gaussian splatting training method; we adapt and regularize training to account for these issues. We present a complete solution, that enables real-time rendering of very large scenes and can adapt to available resources thanks to our LOD method. We show results for captured scenes with up to tens of thousands of images with a simple and affordable rig, covering trajectories of up to several kilometers and lasting up to one hour. Project Page: https://repo-sam.inria.fr/fungraph/hierarchical-3d-gaussians/
title A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2406.12080