neural-3d

A Neural Field-Based Approach for View Computation & Data Exploration in 3D Urban Environments

Neural fields for view computation and data exploration in 3D cities

IEEE TVCG 2026

Direct and inverse view queries over building facades — Direct queries compute what building facades see (buildings, sky, water, trees); inverse queries find the facade positions that meet view constraints set in parallel coordinates.

Exploring 3D urban datasets is often slow and complex due to occlusion and the need for manual viewpoint adjustments. We introduce a neural field-based, view-driven approach that encodes environments into an efficient implicit representation, enabling both direct queries (like visibility or solar analysis) and inverse queries (to find suggested views). Validated through real-world case studies, our method supports urban analysis tasks such as facade visibility, outdoor space evaluation, and assessing new developments.

Publications

A Neural Field-Based Approach for View Computation & Data Exploration in 3D Urban Environments

Stefan Cobeli, Kazi Shahrukh Omar, Rodrigo Valença, Nivan Ferreira, Fabio Miranda

IEEE Transactions on Visualization and Computer Graphics, 2026

Paper arXiv Code

Team

Stefan CobeliUniversity of Illinois Chicago
Kazi OmarUniversity of Illinois Chicago
Rodrigo Valença
Nivan FerreiraUniversidade Federal de Pernambuco
Fabio MirandaUniversity of Illinois Chicago

How to cite

BibTeX

@article{cobeli2026neural,
  title = {A Neural Field-Based Approach for View Computation \& Data Exploration in 3D Urban Environments},
  volume = {32},
  doi = {10.1109/tvcg.2025.3635528},
  number = {2},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  author = {Cobeli, Stefan and Omar, Kazi Shahrukh and Valença, Rodrigo and Ferreira, Nivan and Miranda, Fabio},
  year = {2026},
  month = feb,
  pages = {1540--1553},
  eprint = {2511.14742},
  archiveprefix = {arXiv}
}