CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction

• URL: http://arxiv.org/abs/2503.23044v1
• Date: Sat, 29 Mar 2025 11:33:39 GMT
• Title: CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction
• Authors: Yuanyuan Gao, Hao Li, Jiaqi Chen, Zhengyu Zou, Zhihang Zhong, Dingwen Zhang, Xiao Sun, Junwei Han,
• Abstract summary: CityGS-X is a scalable architecture built on a novel parallelized hybrid hierarchical 3D representation (PH2-3D)<n>It consistently outperforms existing methods in terms of faster training times, larger rendering capacities, and more accurate geometric details in large-scale scenes.
• Score: 79.1905347777988
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite its significant achievements in large-scale scene reconstruction, 3D Gaussian Splatting still faces substantial challenges, including slow processing, high computational costs, and limited geometric accuracy. These core issues arise from its inherently unstructured design and the absence of efficient parallelization. To overcome these challenges simultaneously, we introduce CityGS-X, a scalable architecture built on a novel parallelized hybrid hierarchical 3D representation (PH^2-3D). As an early attempt, CityGS-X abandons the cumbersome merge-and-partition process and instead adopts a newly-designed batch-level multi-task rendering process. This architecture enables efficient multi-GPU rendering through dynamic Level-of-Detail voxel allocations, significantly improving scalability and performance. Through extensive experiments, CityGS-X consistently outperforms existing methods in terms of faster training times, larger rendering capacities, and more accurate geometric details in large-scale scenes. Notably, CityGS-X can train and render a scene with 5,000+ images in just 5 hours using only 4 * 4090 GPUs, a task that would make other alternative methods encounter Out-Of-Memory (OOM) issues and fail completely. This implies that CityGS-X is far beyond the capacity of other existing methods.

Related papers

• CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction [68.81212850946318]
  We propose a multi-agent collaborative fast 3DGS surface reconstruction framework based on distributed learning for large-scale surface reconstruction.<n>Specifically, we develop local model compression (LMC) and model aggregation schemes (MAS) to achieve high-quality surface representation of large scenes.<n>Our proposed method can achieve fast and scalable high-fidelity surface reconstruction and photorealistic rendering.
  arXiv  Detail & Related papers  (2024-12-23T14:31:15Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction [71.08607897266045]
  3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. We make the first attempt to tackle the challenging task of large-scale scene surface reconstruction. We propose GigaGS, the first work for high-quality surface reconstruction for large-scale scenes using 3DGS.
  arXiv  Detail & Related papers  (2024-09-10T17:51:39Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• 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)

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.