Pith. sign in

REVIEW 7 cited by

CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.01133 v3 pith:XHWPB4DG submitted 2024-04-01 cs.CV

classification cs.CV
keywords renderingtraininglarge-scalereal-timeacrossscalessceneapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large-scale 3DGS and rendering it in real-time across various scales remains challenging. This paper introduces CityGaussian (CityGS), which employs a novel divide-and-conquer training approach and Level-of-Detail (LoD) strategy for efficient large-scale 3DGS training and rendering. Specifically, the global scene prior and adaptive training data selection enables efficient training and seamless fusion. Based on fused Gaussian primitives, we generate different detail levels through compression, and realize fast rendering across various scales through the proposed block-wise detail levels selection and aggregation strategy. Extensive experimental results on large-scale scenes demonstrate that our approach attains state-of-theart rendering quality, enabling consistent real-time rendering of largescale scenes across vastly different scales. Our project page is available at https://dekuliutesla.github.io/citygs/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination

    cs.CV 2025-12 conditional novelty 7.0 of 10

    SkyLume contributes 10 real-world UAV urban regions captured at morning, noon, and afternoon with LiDAR-based ground truth, plus the Temporal Consistency Coefficient metric for cross-time albedo stability.

  2. RemVerse: Supporting Reminiscence Activities for Older Adults through AI-Assisted Virtual Reality

    cs.HC 2025-07 conditional novelty 6.0 of 10

    An AI-assisted VR environment with generative visuals and a dialogue agent helped 14 older adults recall, visualize, and elaborate personal memories, with engagement increasing over a single session.

  3. Virtual Memory for 3D Gaussian Splatting

    cs.GR 2025-06 conditional novelty 6.0 of 10

    A proxy-mesh visibility buffer with page streaming and level of detail lets 3D Gaussian Splatting render scenes larger than GPU memory while culling occluded Gaussians.

  4. PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PointGS improves few-shot 3D Gaussian splatting by fusing multi-view image features per 3D point and refining them with a neighbor-attention network before decoding Gaussian colors.

  5. Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

    cs.AR 2025-06 conditional novelty 6.0 of 10

    A mobile 3DGS rendering system that shares sorting across frames, caches pixel colors by significant Gaussian IDs, and adds a custom neural rendering unit to reach 4.5x speedup.

  6. SharpSplat: Edge-Regularized 3D Gaussian Splatting for High Fidelity Urban Building Reconstruction from UAV images

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Aligning rendered Sobel edges to SAM3-masked building edges during 3DGS training modestly improves facade sharpness on UAV urban scenes without changing the Gaussian architecture.

  7. DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management

    cs.RO 2025-11 conditional novelty 5.0 of 10

    Storing inactive spatial chunks of a 3D Gaussian map on disk and loading only camera-visible chunks into GPU memory lets DiskChunGS map all 11 KITTI sequences on a 24 GB GPU without memory failures.

Pith tools