VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
By Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue Liu, Yang Lu, Xiaofei Wu, Songcen Xu, Youliang Yan and 1 more. Computer Vision and Pattern Recognition, 2024
304 citations recorded by the source corpus.
Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-scale and object-centric scenes, scaling it up to large scenes poses challenges due to limited video memory, long optimization time, and noticeable appearance variations. To address these challenges, we present VastGaussian, the first method for high-quality reconstruction and real-time rendering on large scenes based on 3D Gaussian Splatting. We propose a progressive partitioning strategy to divide a large scene into multiple cells, where the training cameras and point cloud are properly distributed with an airspace-aware visibility criterion. These cells are merged into a complete scene after parallel optimization. We also introduce decoupled appearance modeling into the optimization process to reduce appearance variations in the rendered images. Our approach outperforms existing NeRF-based methods and achieves state-of-the-art results on multiple large scene datasets, enabling fast optimization and high-fidelity real-time rendering. Project page: https://vastgaussian.github.io.
Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/930283ab1c699d72dd95720f91d3124ed7f4ea1c
Citations in the corpus
- Recent advances in 3D Gaussian splatting (2024, unknown): “Compared to NeRF, 3DGS is an explicit representation and the implicit deformation modeling requires lots of parameters which may bring overfit, so some explicit deformation modeling methods are also proposed, which ensure fast training.”
- A Survey on 3D Gaussian Splatting (2024, unknown): “Both directions exploit the speed advantage and editability of GS to enable fast training, real-time rendering, and precise control over deformations, while addressing challenges in cross-frame correspondence, topology flexibility, and multi-view consistency.”