AI Paper Atlas

Research map / 3D vision / Gaussian splatting

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

Yuanyuan Gao, Hao Li, Jiaqi Chen, Zhengyu Zou, Zhihang Zhong, Dingwen Zhang, Xiao Sun, Junwei Han

ICCV 2025 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add batch-level RGB training (ablation)CityGS-X · BuildingPSNR: 22.41 -> 23.24; time 4h21m -> 1h48mImproved
add enhanced depth-prior training after batch RGB (ablation)CityGS-X · BuildingPSNR: 23.24 -> 22.46Hurt
add batch-level geometric training on top of depth prior (ablation)CityGS-X · BuildingPSNR: 22.46 -> 22.76Improved
add depth-prior training as a transition before geometric training (ablation)CityGS-X · BuildingPSNR: 22.10 -> 22.76Improved
increase batch size from 2 to 16 with more GPUs (ablation)CityGS-X · RubblePSNR: 25.58 -> 26.25Improved
increase batch size from 8 to 16 (ablation)CityGS-X · RubblePSNR: 26.15 -> 26.25No clear effect
replace partition-and-merge with PH2-3D parallel multi-GPU renderingCityGS-X · MatrixCityPSNR: 27.23 -> 27.58Improved
CityGS-X versus partition-based methods on training timeCityGS-X · Mill19 Buildingtraining time: 03:26 -> 03:00 vs VastGSImproved
add Step 3 geometric training without Step 2 depth transition (ablation)CityGS-X · MatrixCitygeometry quality (qualitative)Hurt

Later papers that compared with this method

1 later accepted paper reports CityGS-X as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy