Research map / 3D vision / 3D generation
Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
Keyang Lu, Sifan Zhou, Hongbin Xu, Gang Xu, Zhifei Yang, Yikai Wang, Zhen Xiao, Jieyi Long, Ming Li
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 hierarchical coarse-to-fine planning (Global Planner + Local Designer) instead of a single-stage planner (ablation) | Yo'City · City prompts | VQAScore: 0.7034 -> 0.7151 | Improved |
| use hierarchical coarse-to-fine planning instead of a single-stage planner (ablation) | Yo'City · City prompts | Layout Coherence win rate (GPT-5): 27.00% -> 73.00% | Improved |
| use hierarchical coarse-to-fine planning instead of a single-stage planner (ablation) | Yo'City · City prompts | Overall Realism win rate (GPT-5): 24.50% -> 75.50% | Improved |
| replace tile-by-tile autoregressive generation (SynCity) with parallel hierarchical grid generation | city generation · City prompts | VQAScore: 0.6975 -> 0.7151 | Improved |
| use produce-refine-evaluate isometric loop vs SynCity at grid level | 3D Generator · Grid-level comparison | Aesthetic Score: 4.95 -> 5.52 | Improved |
| use grid-level alignment from Yo'City instead of SynCity | 3D Generator · Grid-level comparison | Alignment Score: 0.6572 -> 0.6927 | Improved |
| use Yo'City instead of retrieval-based CityCraft | city generation · City prompts | VQAScore: 0.5639 -> 0.7151 | Improved |
| successively expand the city with relationship-guided expansion | Yo'City expansion · Expansion over four steps | VQAScore stability: Coefficient of Variation 3.34% | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SynCity — SynCity: Training-Free Generation of 3D Worlds (ICCV 2025) · better on 3 of 3 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
- CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR 2024 · similarity 0.89)
- MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts (CVPR 2026 · similarity 0.89)
- Generative Gaussian Splatting for Unbounded 3D City Generation (CVPR 2025 · similarity 0.88)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.86)
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent (NeurIPS 2025 · similarity 0.86)
- DeBaRA: Denoising-Based 3D Room Arrangement Generation (NeurIPS 2024 · similarity 0.86)
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.
