This work developed Mask-based Weighted Conditional Flow Matching (MWCFM), which extends Flow Matching by introducing contextual masks for precise feature focusing, which enables targeted training on critical spatial elements relevant to urban planning.
Abstract
In the context of urban planning, architects are normally instructed with creating presentation images that visualize proposed buildings within their urban context. This work aims to develop a GenAI model for automatically generating architectural presentation images in urban scenes, with emphasis on model optimization. To achieve this, we developed Mask-based Weighted Conditional Flow Matching (MWCFM), which extends Flow Matching by introducing contextual masks for precise feature focusing. This enables targeted training on critical spatial elements relevant to urban planning. Our trained model learns from urban street-view data while adhering to specific style-guidelines, which are integrated into training through the loss function. Furthermore, the model's performance is evaluated using application related metrics, derived from presentation image style guidelines.
A perception-aware framework for green streetscape redesign that transforms a real street-view image and a high-level design goal into a realistic visualization of a retrofitted street, and suggests that controllable generative models can provide practical support for urban street retrofit visualization and assessment.
Hongkun Wang, Fei Li· Digital Signal and Computer...· 0 citations
This paper presents a planning-oriented assessment of streetscape qualities in the north-eastern periphery of Nice using the latest release of SAGAI (Streetscape Analysis with Generative AI), an open-source workflow that leverages vision-language models for large-scale streetscape analysis from Google Street View image...
A programmatic generation model for urban road landscapes that integrates three-dimensional convolutional neural networks (3D-CNNs) and attention mechanisms to improve the efficiency and accuracy of road landscape generation is proposed.
Lei Zhang, Xinhui Fu, Huan Zhang· GeoJournal· 0 citations
The feasibility and performance of a Convolutional Neural Network model using spectrally transformed high-resolution multispectral imagery to map roofprints in Washington, District of Columbia (D.C.) and Denver, CO, United States is explored.
C. Amaral, Maxwell C. Cook, Johannes H. Uhl et al.· Remote Sensing· 0 citations
This work presents an end-to-end pipeline for the automatic estimation of the number of storeys to semantically enrich 3D city models and enables the automatic augmentation of CityGMLbased 3D city models by filling in missing attributes.
Lukas Arzoumanidis, Al Maimun As Samee, Elmehdi Kanna et al.· ISPRS Annals of the Photogra...· 0 citations
Click2Poly, a human-in-the-loop AI assistant designed to speed up manual editing of building and wall vector layers in a real-world production environment, is presented.
Nicolas Girard, Jawher Ben Abdallah, Arno Gobbin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
