Research map / 3D vision / Gaussian splatting
DrivingGaussian++: Toward Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
Yajiao Xiong, Xiaoyu Zhou, Yongtao Wang, Deqing Sun, Ming–Hsuan 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 Incremental Static 3D Gaussians (ablation) | DrivingGaussian++ · nuScenes | PSNR: 27.72 -> 28.74 | Improved |
| add Composite Dynamic Gaussian Graph (ablation) | DrivingGaussian++ · nuScenes | PSNR: 26.97 -> 28.74 | Improved |
| add TSSIM loss (ablation) | DrivingGaussian++ · nuScenes | PSNR: 27.88 -> 28.74 | Improved |
| add robust loss (ablation) | DrivingGaussian++ · nuScenes | PSNR: 28.05 -> 28.74 | Improved |
| add LiDAR loss (ablation) | DrivingGaussian++ · nuScenes | PSNR: 28.45 -> 28.74 | Improved |
| initialize with LiDAR prior instead of SfM points | DrivingGaussian++ · nuScenes | PSNR: 28.36 -> 28.74 | Improved |
| initialize with LiDAR instead of random points (ablation) | DrivingGaussian++ · nuScenes | PSNR: 22.23 -> 28.74 | Improved |
| initialize with LiDAR prior instead of pre-trained NeRF points (ablation) | DrivingGaussian++ · nuScenes | PSNR: 28.51 -> 28.74 | Improved |
| use all LiDAR points (2M) instead of filtered 1M (ablation) | DrivingGaussian++ · nuScenes | PSNR: 28.74 -> 28.78 | No clear effect |
| downsample LiDAR to 600K (ablation) | DrivingGaussian++ · nuScenes | PSNR: 28.74 -> 28.49 | Hurt |
| use LiDAR prior instead of SfM | DrivingGaussian++ · KITTI-360 | PSNR: 25.18 -> 25.62 | Improved |
| use 3D Gaussian editing instead of InstructNeRF2NeRF | DrivingGaussian++ · nuScenes editing | Exec. time: 274 minutes -> 8 minutes | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- EmerNeRF — EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision (ICLR 2024) · better on 3 of 3 shared results
- S-NeRF — S-NeRF: Neural Radiance Fields for Street Views (ICLR 2023) · better on 3 of 3 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 0.95)
- SceneCrafter: Controllable Multi-View Driving Scene Editing (CVPR 2025 · similarity 0.90)
- DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving (NeurIPS 2025 · similarity 0.89)
- DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input (AAAI 2025 · similarity 0.88)
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability (NeurIPS 2025 · similarity 0.88)
- FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes (CVPR 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.
