Title:3D city modelling - Machine Learning with Computer Graphics
Posted: April 22, 2016
Location: Paris, France
Description: We aim to individually reconstruct in 3D and evaluate each building using Very High Resolution (VHR) optical images using several state-of-the-art methods.
Detected errors with deep-based methods will be automatically ranked, and a human operator will then validate or invalidate such errors. It will help us (1) robustifying the learning process of acceptable 3D
reconstructions, given a level of details, and (2) upscaling the process with a direct labeling of
Various 3D modeling techniques will be compared in order to assess which one(s) is(are) the most suited for which urban environment. It should give rise to a 3D modeling software able to reconstruct a large range of urban environments.
Application Instructions: All details are available here.
Deadline for application has been extended to May 1.