Research map / 3D vision / Gaussian splatting
CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving
Rui Song, Chenwei Liang, Yan Xia, Walter Zimmer, Hu Cao, Holger Caesar, Andreas Festag, Alois Knoll
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 the Deformation Compensation Network (ablation) | CoDa-4DGS · NOTR Dynamic-32 | PSNR: 31.71 -> 32.98 | Improved |
| deepen the original MLP to match DCN parameter count instead of using DCN (ablation) | 4DGS deformation decoder · NOTR Dynamic-32 | PSNR: 31.71 -> 31.75 | No clear effect |
| add temporal deformation awareness input to DCN (ablation) | CoDa-4DGS · NOTR Dynamic-32 | PSNR: 32.80 -> 32.86 | Improved |
| add context awareness input to DCN (ablation) | CoDa-4DGS · NOTR Dynamic-32 | PSNR: 32.77 -> 32.86 | Improved |
| add time embedding input to DCN (ablation) | CoDa-4DGS · NOTR Dynamic-32 | PSNR: 32.69 -> 32.86 | Improved |
| add CoDa-4DGS as plug-in to vanilla 4DGS | 4DGS · Waymo Scene 22 | PSNR: 32.54 -> 33.12 | Improved |
| add CoDa-4DGS as plug-in to vanilla 4DGS | 4DGS · Waymo Scene 02 | PSNR: 29.14 -> 29.84 | Improved |
| add CoDa-4DGS as plug-in to S3Gaussian | S3Gaussian · Waymo Scene 22 | PSNR: 33.49 -> 34.09 | Improved |
| add CoDa-4DGS as plug-in to S3Gaussian | S3Gaussian · Waymo Scene 02 | PSNR: 30.14 -> 30.37 | Improved |
| add CoDa-4DGS to S3Gaussian, dynamic-object PSNR | S3Gaussian · Waymo Scene 22 | PSNR*: 29.79 -> 31.14 | Improved |
| replace S3Gaussian with CoDa-4DGS on Waymo novel view synthesis | S3Gaussian · Waymo Open (novel view synthesis) | LPIPS: 0.100 -> 0.058 | 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.
- EmerNeRF — EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision (ICLR 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
- DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes (CVPR 2024 · similarity 0.90)
- SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving (CVPR 2025 · similarity 0.90)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.89)
- DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes (CVPR 2025 · similarity 0.89)
- EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene (AAAI 2025 · similarity 0.89)
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering (CVPR 2024 · similarity 0.89)
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.
