AI Paper Atlas

Research map / 3D vision / Gaussian splatting

RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors

Sicong Du, Jiarun Liu, Qifeng Chen, Hao-Xiang Chen, Tai-Jiang Mu, Sheng Yang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 1 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 reward network (ablation)RGE on Scaffold-GS · Para-Lane one-lanePSNR: 19.24 -> 19.72Improved
add reward network (ablation)RGE on Scaffold-GS · Para-Lane one-laneSSIM: 0.544 -> 0.586Improved
add reward network (ablation)RGE on Scaffold-GS · Para-Lane one-lanetraining time (min): 91 -> 89Improved
add differentiated training strategy (ablation)RGE on Scaffold-GS · Para-Lane one-lanePSNR: 19.55 -> 19.72Improved
add differentiated training strategy (ablation)RGE on Scaffold-GS · Para-Lane one-lanetraining time (min): 112 -> 89Improved
apply RGE on 3DGS3DGS · Para-Lane one-lanePSNR: 16.12 -> 18.73Improved
apply RGE on Scaffold-GSScaffold-GS · Para-Lane one-lanePSNR: 17.25 -> 19.72Improved
apply RGE on Scaffold-GSScaffold-GS · Para-Lane two-lanePSNR: 16.70 -> 18.11Improved
apply RGE on Scaffold-GSScaffold-GS · Waymo lane shift @5mFID: 189.25 -> 129.12Improved
apply RGE on Scaffold-GS versus FreeSim*FreeSim* · Waymo lane shift @5mFID: 174.12 -> 129.12Improved
apply RGE on Scaffold-GS versus FreeSim*FreeSim* · Para-Lane one-laneLPIPS: 0.424 -> 0.415Mixed
replace SD with SVD diffusion prior plus RGE (ablation)RGE on Scaffold-GS · Para-Lane one-lanePSNR: 19.72 -> 19.95Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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