# From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation

arXiv: https://arxiv.org/abs/2509.05469 · HTML: https://mlsanity.com/paper/2509.05469/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 66 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [In-Context Learning Unlocked for Diffusion Models](https://mlsanity.com/paper/2305.01115/) (2023)
- [Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion](https://mlsanity.com/paper/2407.13759/) (2024)
- [Cross-view image synthesis using geometry-guided conditional GANs](https://mlsanity.com/paper/1808.05469/) (2018)
- [ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2504.10514/) (2025)
- [NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging](https://mlsanity.com/paper/2403.03485/) (2024)
- [MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation](https://mlsanity.com/paper/2505.02648/) (2025)
- [GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing](https://mlsanity.com/paper/2505.11493/) (2025)
- [Towards Visual Text Grounding of Multimodal Large Language Model](https://mlsanity.com/paper/2504.04974/) (2025)
- [Urban Scene Diffusion through Semantic Occupancy Map](https://mlsanity.com/paper/2403.11697/) (2024)
- [Text2Street: Controllable Text-to-image Generation for Street Views](https://mlsanity.com/paper/2402.04504/) (2024)
- [From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs](https://mlsanity.com/paper/2502.17701/) (2025)
- [RuleR: Improving LLM Controllability by Rule-based Data Recycling](https://mlsanity.com/paper/2406.15938/) (2024)
- [CCA: Collaborative Competitive Agents for Image Editing](https://mlsanity.com/paper/2401.13011/) (2024)
- [Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning](https://mlsanity.com/paper/2405.13326/) (2024)
- [Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance](https://mlsanity.com/paper/2408.04224/) (2024)
- [Generative AI for Urban Planning: Synthesizing Satellite Imagery via Diffusion Models](https://mlsanity.com/paper/2505.08833/) (2025)
- [Causality-informed Rapid Post-hurricane Building Damage Detection in Large Scale from InSAR Imagery](https://mlsanity.com/paper/2310.01565/) (2023)
- [Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation](https://mlsanity.com/paper/2404.18598/) (2024)
- [MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models](https://mlsanity.com/paper/2506.23009/) (2025)
- [CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning](https://mlsanity.com/paper/2507.00045/) (2025)
- [Near-real-time Earthquake-induced Fatality Estimation using Crowdsourced Data and Large-Language Models](https://mlsanity.com/paper/2312.03755/) (2023)
- [URSimulator: Human-Perception-Driven Prompt Tuning for Enhanced Virtual Urban Renewal via Diffusion Models](https://mlsanity.com/paper/2409.14589/) (2024)

## Built on by (most cited first, 3 of 3)

- [Language-Conditioned World Modeling for Visual Navigation](https://mlsanity.com/paper/2603.26741/) (2026)
- [Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach](https://mlsanity.com/paper/2601.03534/) (2026)
- [StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure](https://mlsanity.com/paper/2601.15671/) (2026)

## Abstract (arXiv)

Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering collective deliberation and collaborative decision-making. While AI-assisted generative design shows transformative potential by enabling rapid creation of design scenarios, existing generative approaches typically require large amounts of domain-specific training data and struggle to enable precise spatial variations of design/configuration in complex street-view scenes. We introduce a multi-agent system that edits and redesigns bicycle facilities directly on real-world street-view imagery. The framework integrates lane localization, prompt optimization, design generation, and automated evaluation to synthesize realistic, contextually appropriate designs. Experiments across diverse urban scenarios demonstrate that the system can adapt to varying road geometries and environmental conditions, consistently yielding visually coherent and instruction-compliant results. This work establishes a foundation for applying multi-agent pipelines to transportation infrastructure planning and facility design.