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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add reward network (ablation) | RGE on Scaffold-GS · Para-Lane one-lane | PSNR: 19.24 -> 19.72 | Improved |
| add reward network (ablation) | RGE on Scaffold-GS · Para-Lane one-lane | SSIM: 0.544 -> 0.586 | Improved |
| add reward network (ablation) | RGE on Scaffold-GS · Para-Lane one-lane | training time (min): 91 -> 89 | Improved |
| add differentiated training strategy (ablation) | RGE on Scaffold-GS · Para-Lane one-lane | PSNR: 19.55 -> 19.72 | Improved |
| add differentiated training strategy (ablation) | RGE on Scaffold-GS · Para-Lane one-lane | training time (min): 112 -> 89 | Improved |
| apply RGE on 3DGS | 3DGS · Para-Lane one-lane | PSNR: 16.12 -> 18.73 | Improved |
| apply RGE on Scaffold-GS | Scaffold-GS · Para-Lane one-lane | PSNR: 17.25 -> 19.72 | Improved |
| apply RGE on Scaffold-GS | Scaffold-GS · Para-Lane two-lane | PSNR: 16.70 -> 18.11 | Improved |
| apply RGE on Scaffold-GS | Scaffold-GS · Waymo lane shift @5m | FID: 189.25 -> 129.12 | Improved |
| apply RGE on Scaffold-GS versus FreeSim* | FreeSim* · Waymo lane shift @5m | FID: 174.12 -> 129.12 | Improved |
| apply RGE on Scaffold-GS versus FreeSim* | FreeSim* · Para-Lane one-lane | LPIPS: 0.424 -> 0.415 | Mixed |
| replace SD with SVD diffusion prior plus RGE (ablation) | RGE on Scaffold-GS · Para-Lane one-lane | PSNR: 19.72 -> 19.95 | Improved |
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.
- FreeSim* — FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes (CVPR 2025) · better on 6 of 6 shared results
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · better on 6 of 6 shared results
- ReconDreamer* — ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration (CVPR 2025) · better on 2 of 2 shared results
- Street Gaussians — Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting (ECCV 2024) · better on 2 of 2 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
- DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input (AAAI 2025 · similarity 0.89)
- DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes (CVPR 2025 · similarity 0.89)
- DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes (CVPR 2024 · similarity 0.89)
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.89)
- EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene (AAAI 2025 · similarity 0.88)
- GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Driving (AAAI 2025 · similarity 0.88)
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.
