VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
- URL: http://arxiv.org/abs/2402.17427v1
- Date: Tue, 27 Feb 2024 11:40:50 GMT
- Title: VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
- Authors: Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue
Liu, Yangdi Lu, Xiaofei Wu, Songcen Xu, Youliang Yan, Wenming Yang
- Abstract summary: We present VastGaussian, the first method for high-quality reconstruction and real-time rendering on large scenes based on 3D Gaussian Splatting.
Our approach outperforms existing NeRF-based methods and achieves state-of-the-art results on multiple large scene datasets.
- Score: 59.40711222096875
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Dynamic 3D Gaussian Fields for Urban Areas [60.64840836584623]
We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas.
We propose 4DGF, a neural scene representation that scales to large-scale dynamic urban areas.
arXiv Detail & Related papers (2024-06-05T12:07:39Z) - MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo [54.00987996368157]
We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS)
MVSGaussian achieves real-time rendering with better synthesis quality for each scene.
arXiv Detail & Related papers (2024-05-20T17:59:30Z) - DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing [19.437747560051566]
High-fidelity 3D reconstruction of common indoor scenes is crucial for VR and AR applications.
We extend 3D Gaussian splatting with depth and normal cues to tackle challenging indoor datasets.
We propose an adaptive depth loss based on the gradient of color images, improving depth estimation and novel view synthesis results.
arXiv Detail & Related papers (2024-03-26T16:00:31Z) - SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians [2.2369578015657954]
Implicit neural representation methods have shown impressive advancements in learning 3D scenes from unstructured in-the-wild photo collections.
We introduce a new mechanism to train transient Gaussians to handle the presence of scene occluders in an unsupervised manner.
arXiv Detail & Related papers (2024-03-15T16:00:04Z) - FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting [58.41056963451056]
We propose a few-shot view synthesis framework based on 3D Gaussian Splatting.
This framework enables real-time and photo-realistic view synthesis with as few as three training views.
FSGS achieves state-of-the-art performance in both accuracy and rendering efficiency across diverse datasets.
arXiv Detail & Related papers (2023-12-01T09:30:02Z) - Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering [71.44349029439944]
Recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering quality and speed.
We introduce Scaffold-GS, which uses anchor points to distribute local 3D Gaussians.
We show that our method effectively reduces redundant Gaussians while delivering high-quality rendering.
arXiv Detail & Related papers (2023-11-30T17:58:57Z) - GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system.
Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering.
Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
arXiv Detail & Related papers (2023-11-20T12:08:23Z) - Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene
Reconstruction [29.83056271799794]
Implicit neural representation has paved the way for new approaches to dynamic scene reconstruction and rendering.
We propose a deformable 3D Gaussians Splatting method that reconstructs scenes using 3D Gaussians and learns them in canonical space.
Through a differential Gaussianizer, the deformable 3D Gaussians not only achieve higher rendering quality but also real-time rendering speed.
arXiv Detail & Related papers (2023-09-22T16:04:02Z) - 3D Gaussian Splatting for Real-Time Radiance Field Rendering [4.320393382724066]
We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times.
We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.
arXiv Detail & Related papers (2023-08-08T06:37:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.