REVIEW 14 cited by
CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
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
CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
read the original 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/.
Forward citations
Cited by 14 Pith papers
-
Sky2Ground: A Benchmark for Site Modeling under Varying Altitude
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.
-
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
A geometry and gradient-based partitioning strategy enables scalable block-wise 3D Gaussian Splatting for large-scale panoramic outdoor scenes.
-
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
A real multi-city, multi-kilometer surround-view driving dataset plus an urban-tailored 3DGS baseline shows that city-scale reconstruction still degrades with scale, off-trajectory views, and real-world noise.
-
SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting
SatSplatDiff combines depth supervision and shadow-guided generative refinement with 2DGS to reduce geometric MAE by up to 18% and improve visual fidelity by 28-45% on satellite datasets while enabling 5x resolution e...
-
Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication
Splaxel achieves up to 7.6x speedup in distributed 3DGS training on scenes with up to 120M Gaussians by using pixel-level communication and visibility prediction while preserving reconstruction quality.
-
City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images
City-Mesh3R reconstructs scalable watertight city-scale 3D meshes from multi-view images via topological clustering, distributed SfM, spatial partitioning, and curvature-aware remeshing.
-
TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
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...
-
TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
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.
-
Visually-grounded Humanoid Agents
A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.
-
From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images
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...
-
SharpSplat: Edge-Regularized 3D Gaussian Splatting for High Fidelity Urban Building Reconstruction from UAV images
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.
-
SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting
SatSplatDiff combines depth supervision and shadow-guided generative refinement with prior SatSplat geometry to reduce hallucinations while raising visual quality in satellite 3D reconstruction.
-
Feed-Forward Gaussian Splatting from Sparse Aerial Views
AnyCity reconstructs coherent 3D Gaussian urban scenes from sparse aerial views in one feed-forward pass by anchoring observation-supported geometry and applying gated residual updates conditioned on an aerial-adapted...
-
MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
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...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.