Research map / 3D vision / Gaussian splatting
BezierGS: Dynamic Urban Scene Reconstruction with Bezier Curve Gaussian Splatting
Zipei Ma, Junzhe Jiang, Yurui Chen, Li Zhang
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 inter-curve consistency loss (ablation) | BezierGS · Waymo NVS | PSNR: 30.83 -> 31.51 | Improved |
| add inter-curve consistency loss (ablation) | BezierGS · Waymo NVS | Dyn-PSNR: 26.15 -> 28.51 | Improved |
| add dynamic rendering loss (ablation) | BezierGS · Waymo NVS | SSIM: 0.891 -> 0.903 | Improved |
| add dynamic rendering loss (ablation) | BezierGS · Waymo NVS | PSNR: 30.99 -> 31.51 | Improved |
| add velocity loss (ablation) | BezierGS · Waymo NVS | PSNR: 31.40 -> 31.51 | Improved |
| add time-to-Bezier mapping (ablation) | BezierGS · Waymo NVS | PSNR: 31.36 -> 31.51 | Improved |
| use Bezier curves instead of MLP trajectory (ablation) | BezierGS · Waymo NVS | PSNR: 29.58 -> 31.51 | Improved |
| use Bezier curves instead of sinusoidal trajectory (ablation) | BezierGS · Waymo NVS | PSNR: 29.65 -> 31.51 | Improved |
| use Bezier curves instead of MLP trajectory (ablation) | BezierGS · Waymo NVS | LPIPS: 0.087 -> 0.092 | Hurt |
| learnable Bezier trajectories vs bounding-box methods under noisy annotations | BezierGS · nuPlan NVS | PSNR: +3.04 dB | Improved |
| compare to best baseline | BezierGS · Waymo NVS | Dyn-PSNR: +2.66 dB | 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.
- OmniRe — OmniRe: Omni Urban Scene Reconstruction (ICLR 2025) · better on 6 of 6 shared results
- Street Gaussians — Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting (ECCV 2024) · better on 1 of 1 shared result
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
- DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes (CVPR 2025 · similarity 0.90)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.88)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving (CVPR 2025 · similarity 0.88)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.88)
- SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (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.
