CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
- URL: http://arxiv.org/abs/2411.00771v1
- Date: Fri, 01 Nov 2024 17:59:31 GMT
- Title: CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
- Authors: Yang Liu, Chuanchen Luo, Zhongkai Mao, Junran Peng, Zhaoxiang Zhang,
- Abstract summary: CityGaussianV2 is a novel approach for large-scale scene reconstruction.
We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.
Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
- Score: 53.107474952492396
- License:
- Abstract: Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios, remains a significant challenge due to the unstructured nature of 3DGS. In this paper, we present CityGaussianV2, a novel approach for large-scale scene reconstruction that addresses critical challenges related to geometric accuracy and efficiency. Building on the favorable generalization capabilities of 2D Gaussian Splatting (2DGS), we address its convergence and scalability issues. Specifically, we implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence. To scale up, we introduce an elongation filter that mitigates Gaussian count explosion caused by 2DGS degeneration. Furthermore, we optimize the CityGaussian pipeline for parallel training, achieving up to 10$\times$ compression, at least 25% savings in training time, and a 50% decrease in memory usage. We also established standard geometry benchmarks under large-scale scenes. Experimental results demonstrate that our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs. The project page is available at https://dekuliutesla.github.io/CityGaussianV2/.
Related papers
- ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery [11.706262924395768]
3D-GS often struggles to capture rich details and complete geometry.
We introduce a novel densification method, residual split, which adds a downscaled Gaussian as a residual.
Our approach is capable of adaptively retrieving details and complementing missing geometry while enabling progressive refinement.
arXiv Detail & Related papers (2024-12-10T13:19:27Z) - Quadratic Gaussian Splatting for Efficient and Detailed Surface Reconstruction [7.500927135156425]
Quadratic Gaussian Splatting (QGS) is a novel method that replaces disks with quadric surfaces.
QGS renders spatial curvature to guide the normal consistency term, to effectively reduce over-smoothing.
Our code willbe released as open source.
arXiv Detail & Related papers (2024-11-25T13:55:00Z) - PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.
We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
arXiv Detail & Related papers (2024-06-14T17:53:55Z) - RaDe-GS: Rasterizing Depth in Gaussian Splatting [32.38730602146176]
Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering.
Our work introduces a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods.
arXiv Detail & Related papers (2024-06-03T15:56:58Z) - R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction.
This paper introduces R2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
arXiv Detail & Related papers (2024-05-31T08:39:02Z) - AbsGS: Recovering Fine Details for 3D Gaussian Splatting [10.458776364195796]
3D Gaussian Splatting (3D-GS) technique couples 3D primitives with differentiable Gaussianization to achieve high-quality novel view results.
However, 3D-GS frequently suffers from over-reconstruction issue in intricate scenes containing high-frequency details, leading to blurry rendered images.
We present a comprehensive analysis of the cause of aforementioned artifacts, namely gradient collision.
Our strategy efficiently identifies large Gaussians in over-reconstructed regions, and recovers fine details by splitting.
arXiv Detail & Related papers (2024-04-16T11:44:12Z) - CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians [64.6687065215713]
CityGaussian employs a novel divide-and-conquer training approach and Level-of-Detail (LoD) strategy for efficient large-scale 3DGS training and rendering.
Our approach attains state-of-theart rendering quality, enabling consistent real-time rendering of largescale scenes across vastly different scales.
arXiv Detail & Related papers (2024-04-01T14:24:40Z) - GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques.
We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians.
Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
arXiv Detail & Related papers (2024-02-22T16:00:20Z) - GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes.
With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
arXiv Detail & Related papers (2024-02-15T17:32:50Z)
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.