Research map / 3D vision / Depth and stereo
Camera Calibration From Dynamic Silhouettes Using Motion Barcodes
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 motion-barcode matching to select candidate epipolar lines for RANSAC instead of Sinha's line-sampling method | dynamic-silhouette camera calibration · Kung-Fu | best symmetric epipolar distance after 500K RANSAC hypotheses: 0.51 -> 0.26 | Helped |
| Use motion-barcode matching to select candidate epipolar lines for RANSAC instead of Sinha's line-sampling method | dynamic-silhouette camera calibration · Street Dancer | best symmetric epipolar distance after 500K RANSAC hypotheses: 0.62 -> 0.36 | Helped |
| Use motion-barcode matching to select candidate epipolar lines for RANSAC instead of Sinha's line-sampling method | dynamic-silhouette camera calibration · Dancing Girl | best symmetric epipolar distance after 500K RANSAC hypotheses: 0.72 -> 0.41 | Helped |
| Use motion-barcode matching to select candidate epipolar lines for RANSAC instead of Sinha's line-sampling method | dynamic-silhouette camera calibration · Boxer | best symmetric epipolar distance after 500K RANSAC hypotheses: 1.33 -> 0.39 | Helped |
| Use motion-barcode matching to preselect candidate line pairs | dynamic-silhouette camera calibration · Kung-Fu | symmetric epipolar distance at 5K RANSAC hypotheses: 2.12 -> 0.64 | Helped |
| Use motion-barcode matching to preselect candidate line pairs | dynamic-silhouette camera calibration · Street Dancer | symmetric epipolar distance at 5K RANSAC hypotheses: 2.4 -> 0.97 | Helped |
| Use motion-barcode matching to preselect candidate line pairs | dynamic-silhouette camera calibration · Dancing Girl | symmetric epipolar distance at 5K RANSAC hypotheses: 2.96 -> 0.83 | Helped |
| Use motion-barcode matching to preselect candidate line pairs | dynamic-silhouette camera calibration · Boxer | symmetric epipolar distance at 5K RANSAC hypotheses: 4.02 -> 0.85 | Helped |
| Use motion-barcode candidate matching rather than Sinha's sampling procedure | dynamic-silhouette camera calibration · Kung-Fu, Street Dancer, Dancing Girl, and Boxer | non-linear optimizations needed to reach symmetric epipolar distance 0.8: 134 -> 4; 340 -> 20; 388 -> 9; 2994 -> 12 | Helped |
Closest papers by meaning
- Temporal Epipolar Regions (CVPR 2016 · similarity 0.86)
- Optimal Relative Pose With Unknown Correspondences (CVPR 2016 · similarity 0.84)
- Consistency of Silhouettes and Their Duals (CVPR 2016 · similarity 0.83)
- Globally Optimal Pose from Orthographic Silhouettes (CVPR 2026 · similarity 0.82)
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025 · similarity 0.81)
- WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion (CVPR 2024 · similarity 0.80)
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.