Research map / 3D vision / Depth and stereo
CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization
Ara Jafarzadeh, Manuel López Antequera, Pau Gargallo, Yubin Kuang, Carl Toft, Fredrik Kahl, Torsten Sattler
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 sequence-based (generalized camera) localization instead of single images (ablation) | HLoc · CrowdDriven Massachusetts3 (medium) | median position error (m): 3.91 -> 2.03 | Improved |
| use sequence-based localization instead of single images (ablation) | HLoc · CrowdDriven Boston2 (medium) | median position error (m): 4.68 -> 4.15 | Improved |
| use sequence-based localization instead of single images (ablation) | HLoc · CrowdDriven Burgundy2 (medium) | median position error (m): 7.32 -> 8.05 | Hurt |
| use sequence-based localization instead of single images (ablation) | HLoc · CrowdDriven Boston1 (hard) | median position error (m): 31.75 -> 23.96 | Improved |
| use sequence-based localization on hard datasets (ablation) | D2-Net and HLoc · CrowdDriven hard scenes | localization success | No clear effect |
| use HLoc instead of D2-Net on night scenes | D2-Net · CrowdDriven Massachusetts3 (medium, day-night) | median position error (m): 23.95 -> 3.91 | Improved |
| use D2-Net instead of HLoc on Massachusetts4 style night scene | HLoc · CrowdDriven Boston1 (hard) | median position error (m): 31.75 -> 28.78 | Improved |
| use rectified SIFT instead of SIFT-style learned features under strong viewpoint change | HLoc · CrowdDriven Angers1 (hard) | median position error (m): 46.39 -> 191.62 | Hurt |
| use PixLoc instead of HLoc on strong viewpoint hard scene | HLoc · CrowdDriven Angers1 (hard) | median position error (m): 46.39 -> 21.03 | Improved |
| use S2DHM instead of HLoc on night scene | HLoc · CrowdDriven Massachusetts3 (medium) | median position error (m): 3.91 -> 498.52 | Hurt |
Closest papers by meaning
- Long-Term Visual Localization Revisited (TPAMI 2020 · similarity 0.90)
- Investigating the Role of Image Retrieval for Visual Localization (IJCV 2022 · similarity 0.90)
- Towards Visual Localization Interoperability: Cross-Feature for Collaborative Visual Localization and Mapping (ICCV 2025 · similarity 0.89)
- Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions (CVPR 2018 · similarity 0.89)
- OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization (ECCV 2026 · similarity 0.89)
- GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization (NeurIPS 2025 · similarity 0.88)
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.
