Research map / Graph learning / Graph self-supervised learning
BlockPlanner: City Block Generation With Vectorized Graph Representation
Linning Xu, Yuanbo Xiangli, Anyi Rao, Nanxuan Zhao, Bo Dai, Ziwei Liu, Dahua Lin
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 |
|---|---|---|---|
| add geometry losses Ladj, Lbound and Lmerge (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 92.8 -> 36.9 | Improved |
| add Ladj (ablation) | BlockPlanner (no geometry losses) · NYC-Block (Manhattan subset) | FID: 92.8 -> 64.9 | Improved |
| add Lbound on top of Ladj (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 64.9 -> 55.5 | Improved |
| add Lmerge on top of Ladj and Lbound (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 55.5 -> 36.9 | Improved |
| add Lmerge on top of Ladj and Lbound (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | Sl: 0.33 -> 0.18 | Improved |
| increase message passing iterations from 0 to 3 (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 50.9 -> 36.9 | Improved |
| increase message passing iterations from 0 to 3 (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | Sl: 0.75 -> 0.18 | Improved |
| use ring topology instead of row-wise linear topology (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 47.3 -> 36.9 | Improved |
| use ring topology instead of X-axis linear topology (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 44.8 -> 36.9 | Improved |
| use ring topology instead of row-wise linear topology (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | Sl: 0.12 -> 0.18 | Hurt |
| add position encoding on land lots (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | FID: 47.2 -> 36.9 | Improved |
| add position encoding on land lots (ablation) | BlockPlanner · NYC-Block (Manhattan subset) | Sc: 0.45 -> 0.27 | Improved |
Closest papers by meaning
- GlobalMapper: Arbitrary-Shaped Urban Layout Generation (ICCV 2023 · similarity 0.88)
- CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR 2024 · similarity 0.83)
- Text2City: One-Stage Text-Driven Urban Layout Regeneration (AAAI 2024 · similarity 0.83)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.83)
- Generative Gaussian Splatting for Unbounded 3D City Generation (CVPR 2025 · similarity 0.82)
- CitySTAR: Agent-Driven Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding (NeurIPS 2026 · similarity 0.82)
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.
