Research map / 3D vision / Gaussian splatting
ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking
Xiaobao Wei, Zhangjie Ye, Yuxiang Gu, Zunjie Zhu, Yunfei Guo, Yingying Shen, Shan Zhao, Ming Lu, Haiyang Sun, Bing Wang, Guang Chen, Rongfeng Lu and 1 more
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 feature-level supervision to direct IPM L1 (ablation) | ParkGaussian · ParkRecon3D Scene1 slot-aware ablation | PSNR: 24.94 -> 27.43 | Improved |
| use feature-level supervision instead of direct IPM L1 (ablation) | ParkGaussian · ParkRecon3D Scene1 slot-aware ablation | Precision: 0.62 -> 0.64 | No clear effect |
| use teacher-only slot weighting instead of direct IPM L1 (ablation) | ParkGaussian · ParkRecon3D Scene1 slot-aware ablation | Precision: 0.62 -> 0.90 | Improved |
| use student-only slot weighting instead of direct IPM L1 (ablation) | ParkGaussian · ParkRecon3D Scene3 slot-aware ablation | PSNR: 24.99 -> 26.72 | Mixed |
| mix teacher and student weights with alignment loss instead of teacher-only (ablation) | ParkGaussian · ParkRecon3D Scene1 slot-aware ablation | Precision: 0.90 -> 0.97 | Improved |
| mix teacher and student weights with alignment loss instead of teacher-only (ablation) | ParkGaussian · ParkRecon3D Scene3 slot-aware ablation | PSNR: 28.77 -> 30.27 | Improved |
| mix teacher and student weights with alignment loss instead of student-only (ablation) | ParkGaussian · ParkRecon3D Scene3 slot-aware ablation | Precision: 0.71 -> 0.95 | Improved |
| add perception guidance to reconstruction (GCN) (ablation) | ParkGaussian · ParkRecon3D Scene1 slot detection (GCN-Parking) | Precision: 0.95 -> 0.97 | Improved |
| add perception guidance to reconstruction (DMPR-PS) (ablation) | ParkGaussian · ParkRecon3D Scene3 slot detection (DMPR-PS) | Precision: 0.48 -> 0.47 | No clear effect |
| add perception guidance to reconstruction (DMPR-PS) (ablation) | ParkGaussian · ParkRecon3D Scene1 slot detection (DMPR-PS) | Precision: 0.71 -> 0.74 | Improved |
| ParkGaussian vs 3DGUT | ParkGaussian · ParkRecon3D Scene1 novel view synthesis | PSNR: 28.70 -> 30.09 | Improved |
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.
- OmniRe — OmniRe: Omni Urban Scene Reconstruction (ICLR 2025) · 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
- DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes (CVPR 2024 · similarity 0.87)
- DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input (AAAI 2025 · similarity 0.86)
- 3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline (ICLR 2025 · similarity 0.85)
- EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025 · similarity 0.85)
- DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes (CVPR 2025 · similarity 0.85)
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.84)
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.
