1 code implementation • NeurIPS 2018 • Fangchang Ma, Ulas Ayaz, Sertac Karaman
In this work, we present new theoretical results on convolutional generative neural networks, in particular their invertibility (i. e., the recovery of input latent code given the network output).
1 code implementation • 4 Mar 2017 • Fangchang Ma, Luca Carlone, Ulas Ayaz, Sertac Karaman
We address the following question: is it possible to reconstruct the geometry of an unknown environment using sparse and incomplete depth measurements?