Blog Posts

Home /
Blog Posts

Paper: Heterogeneous graph neural networks for building attribute prediction from hierarchical urban features and cross-view imagery

In this work, we introduce a pipeline that integrates hierarchical urban features and cross-view imagery (remote sensing + street view) into a heterogeneous urban graph for building attribute prediction.

Talk: Invited Guest Lecture at HKUST(GZ) on Urban Visual Intelligence: Street View Imagery in Urban Analytics

Invited guest lecture at HKUST(GZ) on Urban Visual Intelligence, discussing the integration of street view imagery and computer vision in urban analytics, and engaging with faculty and students on data-driven approaches to understanding the built environment.

Paper: OpenFACADES: An open framework for architectural caption and attribute data enrichment via street view imagery

We introduce an open framework leveraging multimodal data to enrich building profiles with objective attributes and semantic descriptors. It automates facade detection, reprojects panoramic views, and predicts multi-attribute data.

Talk: Attending the International Research Colloguium 2025 - GeoMod 3D:Mapping, Modelling & Management at Universiti Teknologi Malaysia

Invited talk at the International Research Colloguium 2025 - GeoMod 3D:Mapping, Modelling & Management held by Faculty of Built Environment and Surveying, Universiti Teknologi Malaysia.

Tutorial: Generating voxel 3D city model for cities worldwide

A tutorial on using Voxcity, a Python package for generating grid-based 3D city models and performing urban simulations. Learn how its generator module automates data integration into voxel-based city models.

Paper: Decoding characteristics of building facades using street view imagery and vision-language model

This study leverages street view imagery and vision-language models to analyze 48,752 building images in Hong Kong, identifying eight building clusters. It demonstrates the potential of scalable SVI-based analyses to capture urban spatial and semantic details, enhancing the understanding of the built environment.

Talk: Visiting University of Cambridge

Traveling with group members of Urban Analytics Lab to share knowledge and engage with Sustainable Design group at University of Cambridge.

Talk: Attending the 19th International Conference on Computational Urban Planning and Urban Management

This study explores how building appearances shape urban perception, using machine learning and survey data to analyze human responses to over 250,000 building images from Singapore, San Francisco, and Amsterdam. Findings reveal how architectural styles influence streetscape perceptions, offering insights for architects and city planners.

Video: Architectural perception and emotional well-being

From the comfort of historic facades to the unease of featureless high-rises, architecture plays a powerful role in shaping our emotions and moods. Here, we share our research into the psychological impact of building exteriors.

Talk: Visiting Shenzhen University and Shenzhen Technology University

Traveling with Prof. Filip Biljecki to share knowledge and engage with the research groups at SZU and SZTU, meeting Prof. Wei Tu and Prof. Tianhong Zhao, and sharing innovative ideas in urban studies and computational methods.