Family, friends and everybody else,

Are you in Paris and tired of visiting the historical monuments of the French capital?

So come to watch my Ph.D. defense in the cœur of the city of lights! Here is when and where:

Monday 25th of November at 2:00 PM

Salle 749, 7ème étage, 45 rue des Saints-Pères

Université Paris Descartes, Paris

https://goo.gl/maps/WTFUVaTQNsaJNkX98

Shall you be interested, please leave your name and email (I will not spam you, promise) in the following so I can organize things better.

Here is a small overview of my work:

Depth estimation from a single image is a key instrument for several applications from robotics to virtual reality. Successful Deep Learning approaches in computer vision tasks as object recognition and classification also benefited the domain of depth estimation. In this thesis, we develop methods for monocular depth estimation with deep neural network by exploring different cues: defocus blur and semantics.  We conduct several experiments to understand the contribution of each cue in terms of generalization and model performance. At first, we propose an efficient convolutional neural network for depth estimation along with a conditional Generative Adversarial framework. Our method achieves performances among the best on standard datasets for depth estimation. Then, we propose to explore defocus blur cues, which is an optical information deeply related to depth. We show that deep models are able to implicitly learn and use this information to improve performance and overcome known limitations of classical Depth-from-Defocus. We also build a new dataset with real focused and defocused images that we use to validate our approach. Finally, we explore the use of semantic information, which brings rich contextual information while learned jointly to depth on a multi-task approach. We validate our approaches with several datasets containing indoor, outdoor and aerial images.

And more info on my website: mcarvalho.ml