Research map / 3D vision / Gaussian splatting
Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion
Otto Seiskari, Jerry Ylilammi, Valtteri Kaatrasalo, Pekka Rantalankila, Matias Turkulainen, Juho Kannala, Esa Rahtu, Arno Solin
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 motion blur compensation via screen-space pixel velocities | Splatfacto 3DGS · Synthetic Cozyroom motion blur | PSNR: 26.63 -> 32.20 | Improved |
| add rolling shutter compensation | Splatfacto 3DGS · Synthetic Cozyroom rolling shutter | PSNR: 19.21 -> 35.84 | Improved |
| add pose optimization with velocity compensation | Splatfacto 3DGS · Synthetic Cozyroom pose noise | PSNR: 16.76 -> 36.30 | Improved |
| apply method to the Pool scene with motion blur | Splatfacto 3DGS · Synthetic Pool motion blur | PSNR: 35.50 -> 35.27 | No clear effect |
| use 3DGS with blur and RS model instead of NeRF-based BAD-NeRF | Ours · Deblur-NeRF BAD-NeRF variant | PSNR: Cozyroom 30.97 -> 31.80; Factory 31.65 -> 30.54 | Mixed |
| add motion blur compensation (ablation) | Ours on smartphone data · Smartphone data average | PSNR: 27.99 -> 28.59 | Improved |
| add rolling shutter compensation (ablation) | Ours on smartphone data · Smartphone data average | PSNR: 27.62 -> 28.59 | Improved |
| add pose optimization (ablation) | Ours on smartphone data · Smartphone data average | PSNR: 27.44 -> 28.59 | Improved |
| add velocity optimization (ablation) | Ours on smartphone data · Smartphone data average | PSNR: 27.65 -> 28.59 | Improved |
| add VIO-based velocity initialization (ablation) | Ours on smartphone data · Smartphone data average | PSNR: 28.19 -> 28.59 | Improved |
| replace built-in rolling shutter modeling by CVR de-rolling preprocessing (ablation) | Ours on smartphone data · Smartphone data average | PSNR: 28.59 -> 26.49 | Hurt |
| enable full blur and RS compensation | Ours · Smartphone data training time | training time (min), average: 19 -> 91 | Hurt |
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.
- BAD-NeRF — BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields (CVPR 2023) · better on 4 of 5 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
- BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting (CVPR 2025 · similarity 0.91)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- SplatFormer: Point Transformer for Robust 3D Gaussian Splatting (ICLR 2025 · similarity 0.89)
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction (NeurIPS 2025 · similarity 0.89)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.89)
- EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction (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.
