Congratulations to Stefan Cobeli and Kazi Omar, PhD students at UIC, on their paper “A Neural Field-Based Approach for View Computation & Data Exploration in 3D Urban Environments” in IEEE Transactions on Visualization and Computer Graphics, with Rodrigo Valença, Nivan Ferreira and Fabio Miranda.

The paper introduces a neural field-based, view-driven method that encodes urban environments into an implicit representation. It supports both direct queries, such as visibility and solar exposure analyses, and inverse queries, such as suggesting promising viewpoints, for tasks like evaluating outdoor spaces and exploring the views of new developments. Cobeli led the writing, modeling and experiments, and Omar the interface and the integration of its components.

Paper, code and model are available at urbantk.org/neural-3d.