Research map / 3D vision / Depth and stereo
Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s)
Wenjie Xue, Jun Yang, Jingmin Wang, Limin Shang
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 a second stereo camera (10 cm baseline) (ablation) | Ours · Synthetic single image | MAE v_z (m/s): 2.95 -> 0.19 | Improved |
| add a second stereo camera (10 cm baseline) (ablation) | Ours · Synthetic single image | MAE v_y (m/s): 4.61 -> 0.23 | Improved |
| add a second stereo camera (10 cm baseline) (ablation) | Ours · Synthetic single image | MAE w_z (rad/s): 27.89 -> 10.13 | Improved |
| add a second frame with 2 ms inter-frame delay (ablation) | Ours · Synthetic single image | MAE v_y (m/s): 4.61 -> 0.12 | Improved |
| add a second frame with 2 ms inter-frame delay (ablation) | Ours · Synthetic single image | MAE w_x (rad/s): 49.82 -> 8.48 | Improved |
| add the spin refinement step (Chamfer alignment across frames) (ablation) | Ours, multi-frame · Synthetic multi-frame | MAE w_z (rad/s): 7.51 -> 1.10 | Improved |
| add the spin refinement step (Chamfer alignment across frames) (ablation) | Ours, multi-frame · Synthetic multi-frame | MAE w_x (rad/s): 8.48 -> 4.58 | Improved |
| add the spin refinement step (Chamfer alignment across frames) (ablation) | Ours, stereo multi-frame · Synthetic stereo multi-frame | MAE w_y (rad/s): 23.98 -> 3.93 | Improved |
| increase sphere radius from 80% to 120% of default (ablation) | Ours, single image · Synthetic radius ablation | MAE w_y (rad/s): 31.54 -> 14.86 | Improved |
| increase sphere radius from 100% to 120% of default (ablation) | Ours, single image · Synthetic radius ablation | MAE v_z (m/s): 2.95 -> 3.63 | Mixed |
| use rolling-shutter formulation instead of global-shutter PnP | Multi-frame · Synthetic multi-frame | MAE v_z (m/s): 30.58 -> 0.36 | Improved |
| use correspondence-free formulation instead of Ait-Aider with GT correspondences | Single image · Synthetic single image | MAE v_z (m/s): 14.33 -> 2.95 | Improved |
Closest papers by meaning
- Occlusion-Aware Rolling Shutter Rectification of 3D Scenes (CVPR 2018 · similarity 0.86)
- Rolling Shutter Correction in Manhattan World (ICCV 2017 · similarity 0.86)
- From Two Rolling Shutters to One Global Shutter (CVPR 2020 · similarity 0.86)
- Bringing Rolling Shutter Images Alive with Dual Reversed Distortion (ECCV 2022 · similarity 0.86)
- Fast Rolling Shutter Correction in the Wild (TPAMI 2023 · similarity 0.86)
- Inverting a Rolling Shutter Camera: Bring Rolling Shutter Images to High Framerate Global Shutter Video (ICCV 2021 · 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.
