Research map / 3D vision / Depth and stereo
Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map
Liu Liu, Hongdong Li, Yuchao Dai
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 global random-walk inference on a co-visibility Markov graph instead of local search | Active Search · Dubrovnik (metric) | average inlier ratio (%): 57.1 -> 81.1 | Improved |
| use global inference instead of local search at inlier threshold 0.8 | Active Search · Dubrovnik (metric) | localized images: 162 -> 516 | Improved |
| use global inference instead of local search at inlier threshold 0.2 | Active Search · Dubrovnik (metric) | localized images: 709 -> 791 | Improved |
| use global inference instead of Active Search on median error | Active Search · Dubrovnik (metric) | median error (m): 1.40 -> 0.70 | Improved |
| use global inference instead of Active Search on images under 18.3m | Active Search · Dubrovnik (metric) | images with error <18.3m: 704 -> 743 | Improved |
| use global inference instead of Active Search on SF-0 | Active Search · SF-0 (GPS-restricted region) | localized images (of 803): 31 -> 652 | Improved |
| use global inference instead of Active Search on query time (Dubrovnik 1.73s, Rome 2.35s) | Active Search · Rome and Vienna | query time: slower on Rome and Vienna: 2.35s and 1.67s | Hurt |
Closest papers by meaning
- Efficient & Effective Prioritized Matching for Large-Scale Image-Based Localization (TPAMI 2016 · similarity 0.91)
- Is Geometry Enough for Matching in Visual Localization? (ECCV 2022 · similarity 0.89)
- Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization? (CVPR 2017 · similarity 0.89)
- Yes, we CANN: Constrained Approximate Nearest Neighbors for Local Feature-Based Visual Localization (ICCV 2023 · similarity 0.88)
- Learning to Produce Semi-dense Correspondences for Visual Localization (CVPR 2024 · similarity 0.88)
- Fully Geometric Panoramic Localization (CVPR 2024 · 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.
