Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

URSimulator: Human-Perception-Driven Prompt Tuning for Enhanced Virtual Urban Renewal via Diffusion Models

Chuanbo Hu, Shan Jia, Xin Li

TL;DR

This paper develops a prompt tuning approach that integrates text-driven Stable Diffusion with human perception feedback, iteratively editing local areas of street view images to better align with perceptions of beauty, liveliness, and safety, and demonstrates its effectiveness in simulating urban renewal.

Abstract

Tackling Urban Physical Disorder (e.g., abandoned buildings, litter, messy vegetation, graffiti) is essential, as it negatively impacts the safety, well-being, and psychological state of communities. Urban Renewal is the process of revitalizing these neglected and decayed areas within a city to improve the physical environment and quality of life for residents. Effective urban renewal efforts can transform these environments, enhancing their appeal and livability. However, current research lacks simulation tools that can quantitatively assess and visualize the impacts of renewal efforts, often relying on subjective judgments. Such tools are crucial for planning and implementing effective strategies by providing a clear visualization of potential changes and their impacts. This paper presents a novel framework addressing this gap by using human perception feedback to simulate street environment enhancement. We develop a prompt tuning approach that integrates text-driven Stable Diffusion with human perception feedback, iteratively editing local areas of street view images to better align with perceptions of beauty, liveliness, and safety. Our experiments show that this framework significantly improves perceptions of urban environments, with increases of 17.60% in safety, 31.15% in beauty, and 28.82% in liveliness. In contrast, advanced methods like DiffEdit achieve only 2.31%, 11.87%, and 15.84% improvements, respectively. We applied this framework across various virtual scenarios, including neighborhood improvement, building redevelopment, green space expansion, and community garden creation. The results demonstrate its effectiveness in simulating urban renewal, offering valuable insights for urban planning and policy-making.

URSimulator: Human-Perception-Driven Prompt Tuning for Enhanced Virtual Urban Renewal via Diffusion Models

TL;DR

This paper develops a prompt tuning approach that integrates text-driven Stable Diffusion with human perception feedback, iteratively editing local areas of street view images to better align with perceptions of beauty, liveliness, and safety, and demonstrates its effectiveness in simulating urban renewal.

Abstract

Tackling Urban Physical Disorder (e.g., abandoned buildings, litter, messy vegetation, graffiti) is essential, as it negatively impacts the safety, well-being, and psychological state of communities. Urban Renewal is the process of revitalizing these neglected and decayed areas within a city to improve the physical environment and quality of life for residents. Effective urban renewal efforts can transform these environments, enhancing their appeal and livability. However, current research lacks simulation tools that can quantitatively assess and visualize the impacts of renewal efforts, often relying on subjective judgments. Such tools are crucial for planning and implementing effective strategies by providing a clear visualization of potential changes and their impacts. This paper presents a novel framework addressing this gap by using human perception feedback to simulate street environment enhancement. We develop a prompt tuning approach that integrates text-driven Stable Diffusion with human perception feedback, iteratively editing local areas of street view images to better align with perceptions of beauty, liveliness, and safety. Our experiments show that this framework significantly improves perceptions of urban environments, with increases of 17.60% in safety, 31.15% in beauty, and 28.82% in liveliness. In contrast, advanced methods like DiffEdit achieve only 2.31%, 11.87%, and 15.84% improvements, respectively. We applied this framework across various virtual scenarios, including neighborhood improvement, building redevelopment, green space expansion, and community garden creation. The results demonstrate its effectiveness in simulating urban renewal, offering valuable insights for urban planning and policy-making.
Paper Structure (29 sections, 3 equations, 3 figures, 6 tables, 1 algorithm)

This paper contains 29 sections, 3 equations, 3 figures, 6 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Urban Physical Disorder and Urban Renewal
  4. Advanced Simulation Tools for Enhancing Urban Renewal Planning
  5. Human Perception Based on Street View Imagery
  6. Image Editing and Prompt Engineering
  7. Methodology
  8. Problem Formulation
  9. Framework Overview
  10. Urban Renewal Quantitative Metrics: Assessing Human Perception within Street View Imagery
  11. Strategies for Urban Renewal Simulation: Text-Driven Image Editing
  12. Enhancing Urban Renewal: Prompt Tuning via Bayesian Optimization
  13. Experiments
  14. Experimental Settings
  15. Comparison Analysis of Urban Renewal Strategies
  16. ...and 14 more sections

Figures (3)

  • Figure 1: Example of Urban Renewal Simulation Using Street View Images: (a) Street view depicting physical disorder factor (messy vegetation); (b) Vegetation renewal achieved through image editing.
  • Figure 2: Framework of Prompt Tuning-Guided Urban Renewal. Green text represents input/output, red text indicates trigger words $Tr_W$, and blue text denotes target words $Ta_W$ in the prompt; Gray Panel Represents UPDExplainer hu2023updexplainer; Orange Panel Represents Proposed Framework
  • Figure 3: Two Strategies for Urban Renewal Simulation: Text-Driven Image Editing (a) Our strategy; (b) Diffedit