The reviewed record of science sign in
Pith

arxiv: 2503.23044 · v1 · pith:LW7FUBOS · submitted 2025-03-29 · cs.CV

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LW7FUBOSrecord.jsonopen to challenge →

classification cs.CV
keywords citygs-xarchitectureefficientlarge-scalemethodsrenderingsceneaccurate
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Sky2Ground: A Benchmark for Site Modeling under Varying Altitude

    cs.CV 2026-03 conditional novelty 7.0

    Sky2Ground provides a new three-view multi-altitude dataset and SkyNet model that improves absolute pose estimation performance by 9.6% on RRA@5 and 18.1% on RTA@5 over prior methods when satellite imagery is included.

  2. City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images

    cs.CV 2026-05 unverdicted novelty 6.0

    City-Mesh3R reconstructs scalable watertight city-scale 3D meshes from multi-view images via topological clustering, distributed SfM, spatial partitioning, and curvature-aware remeshing.

  3. TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization

    cs.CV 2026-05 unverdicted novelty 6.0

    TideGS scales 3D Gaussian Splatting training to over one billion primitives on a single 24GB GPU via block-virtualized geometry, asynchronous I/O pipelines, and trajectory-adaptive differential streaming.

  4. TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization

    cs.CV 2026-05 unverdicted novelty 6.0

    TideGS scales 3D Gaussian Splatting to over one billion primitives on a single 24 GB GPU by using block-virtualized geometry, asynchronous I/O pipelines, and trajectory-adaptive differential streaming to exploit train...

  5. DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles

    cs.CV 2026-02 unverdicted novelty 6.0

    DAV-GSWT uses diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal observations while preserving visual quality and tile transitions.

  6. From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images

    cs.CV 2025-12 unverdicted novelty 6.0

    A technique reconstructs large urban areas from sparse extreme off-nadir satellite images by modeling geometry as a Z-monotonic 2.5D height map SDF and applying a generative network to restore plausible textures on th...

  7. MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes

    cs.CV 2025-11 unverdicted novelty 5.0

    MetroGS combines distributed 2D Gaussian Splatting with structured dense enhancement, progressive hybrid optimization, and depth-guided appearance modeling to deliver higher geometric accuracy and stability in large-s...