March 29, 2024, 4:46 a.m. | Tom Kelly, John Femiani, Peter Wonka

cs.CV updates on arXiv.org arxiv.org

arXiv:2310.08471v2 Announce Type: replace
Abstract: We present WinSyn, a unique dataset and testbed for creating high-quality synthetic data with procedural modeling techniques. The dataset contains high-resolution photographs of windows, selected from locations around the world, with 89,318 individual window crops showcasing diverse geometric and material characteristics. We evaluate a procedural model by training semantic segmentation networks on both synthetic and real images and then comparing their performances on a shared test set of real images. Specifically, we measure the difference …

abstract arxiv crops cs.cv cs.gr data dataset diverse locations material modeling photographs quality resolution synthetic synthetic data type windows world

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Robotics Technician - 3rd Shift

@ GXO Logistics | Perris, CA, US, 92571