Research map / 3D vision / Depth and stereo
Rolling Shutter Correction in Manhattan World
Pulak Purkait, Christopher Zach, Ales Leonardis
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 |
|---|---|---|---|
| use Manhattan-world vanishing directions jointly with RS motion instead of line straightness | RS correction · Synthetic X-axis motion | Hmre (pixels): 9.78 -> 3.35 | Improved |
| use Manhattan-world vanishing directions jointly with RS motion | RS correction · Synthetic Y-axis motion | Hmre (pixels): 4.90 -> 1.03 | Improved |
| use Manhattan-world vanishing directions jointly with RS motion | RS correction · Synthetic Z-axis motion | Hmre (pixels): 1.04 -> 0.70 | Improved |
| use single-image method instead of Rengarajan et al. | RS correction · clip03.mov | inliers |RF|: 186.44 -> 212.39 | Improved |
| use single-image method instead of Rengarajan et al. | RS correction · nxs_wobble_6_dual.mov | inliers |RF|: 229.44 -> 239.83 | Improved |
| use single-image method instead of multi-image method [13] | RS correction · nxs_wobble_6_dual.mov | inliers |RF|: 237.27 -> 239.83 | No clear effect |
| use single-image method instead of gyroscope-based [17] | RS correction · gyroscope sequence | inliers |RF|: 148.90 -> 208.64 | Improved |
| use aesthetic gauge fixing (one VD vertical) instead of natural gauge (zero first-row rotation) (ablation) | joint estimation · Synthetic RS image | mean angular error (degrees): 0.25 -> 0.18 | Improved |
| replace per-image line-arc optimization of [27] with VD-based joint estimation | RS correction · runtime 360x520 | seconds: 45 -> 0.3 | Improved |
Closest papers by meaning
- From Two Rolling Shutters to One Global Shutter (CVPR 2020 · similarity 0.92)
- Learning Structure-And-Motion-Aware Rolling Shutter Correction (CVPR 2019 · similarity 0.91)
- A Robust Method for Strong Rolling Shutter Effects Correction Using Lines With Automatic Feature Selection (CVPR 2018 · similarity 0.91)
- From Bows to Arrows: Rolling Shutter Rectification of Urban Scenes (CVPR 2016 · similarity 0.89)
- Rolling Shutter Correction with Intermediate Distortion Flow Estimation (CVPR 2024 · similarity 0.87)
- Single Image Rolling Shutter Removal with Diffusion Models (AAAI 2025 · similarity 0.87)
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.
