Research map / Detection and segmentation / CNN features
Topological Map Extraction From Overhead Images
Zuoyue Li, Jan Dirk Wegner, Aurelien Lucchi
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 direct polygon prediction (PolyMapper) instead of Mask R-CNN | building extraction · crowdAI buildings | AP: 41.9 -> 55.7 | Improved |
| use direct polygon prediction (PolyMapper) instead of PANet | building extraction · crowdAI buildings | AP: 50.7 -> 55.7 | Improved |
| use PolyMapper instead of PANet for large buildings | building extraction · crowdAI buildings | APL: 65.8 -> 58.4 | Hurt |
| use PolyMapper instead of RoadTracer on the RoadTracer dataset | road extraction · RoadTracer dataset roads | SP 10%: 61.8 -> 61.1 | No clear effect |
| use PolyMapper instead of DeepRoadMapper | road extraction · RoadTracer dataset roads | SP 10%: 15.6 -> 61.1 | Improved |
| use PolyMapper instead of RoadTracer | road extraction · PolyMapper dataset roads | SP 10%: 77.7 -> 85.3 | Improved |
| use PolyMapper instead of RoadTracer | road extraction · PolyMapper dataset roads | AP90: 75.4 -> 86.5 | Improved |
| use PolyMapper instead of Mask R-CNN | building extraction · PolyMapper dataset buildings | AP: 42.0 -> 44.7 | Improved |
| use PolyMapper polygons instead of RoadTracer graphs (vertices) | road graph complexity · RoadTracer test set (15 cities) | #vertices: 271,244 -> 31,749 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- RoadTracer — RoadTracer: Automatic Extraction of Road Networks From Aerial Images (CVPR 2018) · better on 5 of 8 shared results
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Regularized Primitive Graph Learning for Unified Vector Mapping (ICCV 2023 · similarity 0.88)
- DeepRoadMapper: Extracting Road Topology From Aerial Images (ICCV 2017 · similarity 0.87)
- LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction (ECCV 2026 · similarity 0.86)
- PolyWorld: Polygonal Building Extraction With Graph Neural Networks in Satellite Images (CVPR 2022 · similarity 0.86)
- Translating Images to Road Network: A Sequence-to-Sequence Perspective (TPAMI 2025 · similarity 0.85)
- Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · 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.
