Research map / 3D vision / Depth and stereo
Relative Pose From a Calibrated and an Uncalibrated Smartphone Image
Yaqing Ding, Daniel Barath, Jian Yang, Zuzana Kukelova
Check 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 the four-point gravity-aware solver instead of E6fs | GC-RANSAC relative pose estimation · PHONE | rotation error MED (°): 2.31 -> 0.59 | Improved |
| Use the four-point gravity-aware solver instead of E6fs | GC-RANSAC relative pose estimation · PHONE | translation error MED (°): 30.65 -> 16.55 | Improved |
| Use the four-point gravity-aware solver instead of E6fs | GC-RANSAC relative pose estimation · PHONE | relative focal length error MED (%): 0.50 -> 0.30 | Improved |
| Use the four-point gravity-aware solver instead of F7 | GC-RANSAC relative pose estimation · PHONE | RANSAC iterations AVG: 776 -> 101 | Improved |
| Use the four-point gravity-aware solver instead of F7 | GC-RANSAC relative pose estimation · PHONE | inliers AVG: 1100 -> 1370 | Improved |
| Use the linear non-minimal solver instead of E6fs | GC-RANSAC relative pose estimation · PHONE | rotation error AVG (°): 4.75 -> 1.05 | Improved |
| Use the linear non-minimal solver instead of E6fs | GC-RANSAC relative pose estimation · PHONE | relative focal length error AVG (%): 1.58 -> 1.25 | Improved |
| Use the four-point gravity-aware solver instead of E5fv | Relative pose estimation · PHONE first sequence | relative focal length error MED (%): 20.35 -> 1.16 | Improved |
| Use the four-point gravity-aware solver instead of E5fv | Relative pose estimation · PHONE first sequence | translation error AVG (°): 9.52 -> 5.60 | Improved |
| Use the Sturm-sequence implementation of E4fs instead of its polynomial-eigenvalue implementation | E4fs · solver runtime | runtime (µs): 51 -> 24 | Improved |
Closest papers by meaning
- Minimal Solutions to Relative Pose Estimation From Two Views Sharing a Common Direction With Unknown Focal Length (CVPR 2020 · similarity 0.91)
- Practical Solutions to the Relative Pose of Three Calibrated Cameras (CVPR 2025 · similarity 0.90)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.89)
- Semicalibrated Relative Pose from an Affine Correspondence and Monodepth (ECCV 2024 · similarity 0.89)
- An Efficient Solution to the Homography-Based Relative Pose Problem With a Common Reference Direction (ICCV 2019 · similarity 0.89)
- Minimal Solvers for Relative Pose Estimation of Multi-Camera Systems using Affine Correspondences (IJCV 2022 · similarity 0.89)
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.
