Research map / Graph learning / Graph self-supervised learning
Neural Turtle Graphics for Modeling City Road Layouts
Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, Ming-Yu Liu, Antonio Torralba, Sanja Fidler
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 |
|---|---|---|---|
| start generation from a pre-stored high-connectivity root (NTG-enhance) | NTG · RoadNet city generation | perceptual rating: 66.0 -> 77.3 | Improved |
| start generation from a pre-stored high-connectivity root (NTG-enhance) | NTG · RoadNet city generation | urban planning rating: 86.5 -> 92.4 | Improved |
| start generation from a pre-stored high-connectivity root (NTG-enhance) | NTG · RoadNet city generation | diversity: 41.27 -> 42.09 | Mixed |
| use NTG instead of PGGAN for generation | NTG-enhance · RoadNet city generation | diversity: 5.95 -> 42.09 | Improved |
| add image-conditioned NTG-I on top of NTG-P | NTG (DLA+STEAL) · SpaceNet road parsing (standard split) | IOU: 59.29 -> 63.15 | Improved |
| add image-conditioned NTG-I on top of NTG-P | NTG (DLA+STEAL) · SpaceNet road parsing (standard split) | APLS: 70.99 -> 74.97 | Improved |
| add NTG map prior as postprocessing to DLA+STEAL | DLA+STEAL · SpaceNet road parsing (standard split) | IOU: 58.96 -> 59.29 | Improved |
| add NTG map prior as postprocessing to DLA+STEAL | DLA+STEAL · SpaceNet road parsing (one city held out) | IOU: 33.94 -> 35.16 | Improved |
| add NTG map prior as postprocessing to DLA+STEAL | DLA+STEAL · SpaceNet road parsing (one city held out) | APLS: 56.15 -> 57.89 | Improved |
Closest papers by meaning
- TD-Road: Top-Down Road Network Extraction with Holistic Graph Construction (ECCV 2022 · similarity 0.87)
- Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · similarity 0.85)
- GlobalMapper: Arbitrary-Shaped Urban Layout Generation (ICCV 2023 · similarity 0.85)
- Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach (ICCV 2023 · similarity 0.85)
- Mastering Spatial Graph Prediction of Road Networks (ICCV 2023 · similarity 0.85)
- Translating Images to Road Network: A Sequence-to-Sequence Perspective (TPAMI 2025 · similarity 0.85)
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.
