Research map / Detection and segmentation / Open-set and few-shot detection
LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment
Shuaibang Peng, Juelin Zhu, Xia Li, Kun Yang, Yu Liu, Maojun Zhang, Shen Yan
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 instance silhouette alignment instead of semantic, same training data (ablation) | LoD-Loc v3 · Tokyo-LoDv3 Grid-Traj | recall (2m,2deg): 22.70 -> 39.30 | Improved |
| use instance silhouette alignment instead of semantic, same training data (ablation) | LoD-Loc v3 · Swiss-EPFLv2 in-Place | recall (2m,2deg): 11.90 -> 58.60 | Improved |
| use instance silhouette alignment instead of semantic, same training data (ablation) | LoD-Loc v3 · UAVD4L-LoDv2 in-Traj | recall (2m,2deg): 71.40 -> 97.60 | Improved |
| keep instance masks separate instead of merging into one mask (ablation) | LoD-Loc v3 alignment · Tokyo-LoDv3 Grid-Traj | recall (2m,2deg): 19.60 -> 38.10 | Improved |
| train on synthetic InsLoD-Loc instead of in-distribution data | LoD-Loc v3 · UAVD4L-LoDv2 out-of-Traj | recall (2m,2deg): 97.90 -> 97.40 | No clear effect |
| LoD-Loc v3 vs v2 in dense scenes | LoD-Loc v3 · Tokyo-LoDv3 Sequence-Traj | recall (2m,2deg): 2.30 -> 49.80 | Improved |
| add fine refinement stage (ablation) | LoD-Loc v3 · Tokyo-LoDv3 Grid-Traj | recall (2m,2deg): 35.00 -> 39.30 | No clear effect |
| use confidence-based weighting instead of area-based (ablation) | LoD-Loc v3 · Tokyo-LoDv3 | recall (2m,2deg): 38.10 -> 39.30 (Grid); 49.80 -> 50.30 (Seq) | No clear effect |
Closest papers by meaning
- LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment (ICCV 2025 · similarity 0.93)
- SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models (ECCV 2026 · similarity 0.89)
- LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment (NeurIPS 2024 · similarity 0.88)
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (CVPR 2024 · similarity 0.86)
- 360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries (CVPR 2024 · similarity 0.85)
- From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-Localization (AAAI 2025 · similarity 0.84)
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.
