| | Title: 3D city modelling - Machine Learning with Computer Graphics | Posted: April 22, 2016 | | Company/Institution: IGN | | 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
new areas.
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. |
|
