AI Paper Atlas

Research map / 3D vision / Gaussian splatting

S3R-GS: Streamlining the Pipeline for Large-Scale Street Scene Reconstruction

Guangting Zheng, Jiajun Deng, Xiaomeng Chu, Yu Yuan, Houqiang Li, Yanyong Zhang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 2 citations (OpenAlex)

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 NeuralODE motion model to 2D-box decomposition (ablation)S3R-GS · KITTI NVS benchmark (75%)PSNR: 21.09 -> 30.48Improved
replace 3D boxes with 2D boxes + NeuralODE (ablation)S3R-GS · KITTI NVS benchmark (75%)PSNR: 31.49 -> 30.48Hurt
use naive 2D boxes with learnable poses instead of 3D boxes (ablation)S3R-GS · KITTI NVS benchmark (75%)PSNR: 31.49 -> 21.09Hurt
add BEV-semantic initialization augmentation (ablation)S3R-GS · KITTI 0011 (75%)PSNR: 24.21 -> 24.66Improved
add BEV-semantic initialization augmentation (ablation)S3R-GS · KITTI NVS benchmark (75%)PSNR: 31.49 -> 31.54Improved
add BEV-semantic initialization augmentation (ablation)S3R-GS · KITTI 0011 (75%)LPIPS: 0.184 -> 0.171Improved
use S3R-GS streamlined pipeline instead of 4DGF pipelineS3R-GS · Argoverse 2reconstruction time (hours): 54.39 h -> 26.71 hImproved
use S3R-GS streamlined pipeline instead of 4DGF pipelineS3R-GS · KITTI 0009reconstruction time (hours): 15.69 h -> 3.02 hImproved
use S3R-GS streamlined pipeline instead of 4DGF pipelineS3R-GS · KITTI 0020reconstruction time (hours): 18.04 h -> 3.37 hImproved
use S3R-GS instead of 4DGFS3R-GS · Argoverse 2PSNR: 24.97 -> 25.68Improved
use S3R-GS instead of 4DGFS3R-GS · KITTI 0009PSNR: 22.64 -> 23.86Improved
use S3R-GS instead of 4DGFS3R-GS · KITTI NVS benchmark (25%)PSNR: 29.08 -> 29.76Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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