Research map / Learning theory and algorithms / Combinatorial and search optimization
Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution
Read the paperCheck 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 |
|---|---|---|---|
| Add measurement normalization to weighted RSBA (ablation) | NW-RSBA · RSSfM, TUM-RSVI and WHU-RSVI | ATE (m): 0.013 -> 0.007 | Helped |
| Add covariance weighting to normalized RSBA (ablation) | NW-RSBA · RSSfM, TUM-RSVI and WHU-RSVI | ATE (m): 0.020 -> 0.007 | Helped |
| Use two-stage Schur complement instead of no Schur complement (ablation) | NW-RSBA · RSSfM, TUM-RSVI and WHU-RSVI | Runtime (s): 16.9 -> 9.8 | Helped |
| Use two-stage instead of one-stage Schur complement (ablation) | NW-RSBA · RSSfM, TUM-RSVI and WHU-RSVI | Runtime (s): 13.0 -> 9.8 | Helped |
| Use measurement normalization rather than direct measurements | RSBA · Synthetic data | RSBA accuracy | Helped |
| Use normalized covariance-weighted residuals | NW-RSBA · Synthetic data, varying speed and image noise | Reconstruction and pose errors | Helped |
| Use normalized covariance-weighted residuals under parallel readout | NW-RSBA · Synthetic degeneracy scene | Reconstruction error | Helped |
| Add NW-RSBA to Orb-SLAM rather than using Orb-SLAM alone | Orb-SLAM · TUM-RSVI and WHU-RSVI RS sequences | Tracking duration: 0.50 -> 1 | Helped |
| Add NW-RSBA to Orb-SLAM rather than NM-RSBA | Orb-SLAM · TUM-RSVI #1, RS data | ATE: 0.115 -> 0.011 | Helped |
| Add NW-RSBA to Orb-SLAM rather than NM-RSBA | Orb-SLAM · TUM-RSVI #7, RS data | ATE: 0.251 -> 0.260 | Hurt |
Closest papers by meaning
- Rolling Shutter Correction with Intermediate Distortion Flow Estimation (CVPR 2024 · similarity 0.83)
- Order-One Rolling Shutter Cameras (CVPR 2025 · similarity 0.82)
- USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields (ICLR 2024 · similarity 0.81)
- Single Image Rolling Shutter Removal with Diffusion Models (AAAI 2025 · similarity 0.81)
- Matrix-Free Shared Intrinsics Bundle Adjustment (CVPR 2025 · similarity 0.81)
- EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling (CVPR 2024 · similarity 0.78)
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.