Research map / 3D vision / Depth and stereo
Learning Structure-And-Motion-Aware Rolling Shutter Correction
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use SMARSC rectification before VisualSFM instead of running SfM directly on RS images | VisualSFM · 47 real RS images | SfM failure runs (of 10): 4 -> 0 | Helped |
| Use SMARSC rectification before VisualSFM instead of MH rectification | VisualSFM · 47 real RS images | SfM failure runs (of 10): 7 -> 0 | Helped |
| Use SMARSC rectification before VisualSFM instead of 2DCNN rectification | VisualSFM · 47 real RS images | SfM failure runs (of 10): 9 -> 0 | Helped |
| Crop training images rather than resize them (ablation) | SMARSC · Synthetic test images with wx-only rotation | wx prediction error | Helped |
| Crop training images rather than resize them (ablation) | SMARSC · Synthetic test images with wy-only rotation | wy prediction error | Helped |
| Crop training images rather than resize them (ablation) | SMARSC · Synthetic test images with wz-only rotation | wz prediction error | Helped |
| Use estimated depth instead of ground-truth depth (ablation) | SMARSC rectification · Synthetic RS images with pure translation | undistortion flow error | No clear effect |
| Use 16 depth bins instead of continuous ground-truth depth (ablation) | SMARSC rectification · Synthetic RS images with pure translation | undistortion flow error | Hurt |
| Use 4 depth bins instead of continuous ground-truth depth (ablation) | SMARSC rectification · Synthetic RS images with pure translation | undistortion flow error | Hurt |
| Use 1 depth bin instead of continuous ground-truth depth (ablation) | SMARSC rectification · Synthetic RS images with pure translation | undistortion flow error | Hurt |
Closest papers by meaning
- Unrolling the Shutter: CNN to Correct Motion Distortions (CVPR 2017 · similarity 0.93)
- Single Image Rolling Shutter Removal with Diffusion Models (AAAI 2025 · similarity 0.88)
- Rolling Shutter Correction with Intermediate Distortion Flow Estimation (CVPR 2024 · similarity 0.88)
- USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields (ICLR 2024 · similarity 0.87)
- Order-One Rolling Shutter Cameras (CVPR 2025 · similarity 0.87)
- Motion Blur Decomposition with Cross-shutter Guidance (CVPR 2024 · similarity 0.86)
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.