Research map / Image generation / Image restoration
Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images
Leonardo Citraro, Mateusz Koziński, Pascal Fua
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 the new OPT-P/OPT-J/OPT-G metrics instead of existing metrics to rank methods | road network reconstruction evaluation · RoadTracer dataset | ranking consistency across metrics | Improved |
| use the new metrics instead of existing metrics to rank methods | road network reconstruction evaluation · DeepGlobe dataset | ranking consistency across metrics | Improved |
| penalize spurious roads via OPT-P instead of APLS/TLTS | APLS and TLTS metrics · overconnections on synthetic benchmark | metric sensitivity | Improved |
| use the three new scores as a group instead of triplets of existing scores | metric correlation analysis · RoadTracer dataset | average pairwise correlation | Improved |
Closest papers by meaning
- RoadTracer: Automatic Extraction of Road Networks From Aerial Images (CVPR 2018 · similarity 0.88)
- Beyond Road Extraction: A Dataset for Map Update Using Aerial Images (ICCV 2021 · similarity 0.87)
- RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction (CVPR 2026 · similarity 0.87)
- DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction (ECCV 2026 · similarity 0.86)
- Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · similarity 0.83)
- AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis (CVPR 2025 · similarity 0.83)
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.
