8 papers
Distilled Semantics for Comprehensive Scene Understanding from Videos
Fabio Tosi, Filippo Aleotti, Pierluigi Zama Ramirez +4
Whole understanding of the surroundings is paramount to autonomous systems. Recent works have shown that deep neural networks can learn geometry (depth) and motion (optical flow) f…
Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models
Alessandro Berlati, Oliver Scheel, Luigi Di Stefano +1
Ambiguity is inherently present in many machine learning tasks, but especially for sequential models seldom accounted for, as most only output a single prediction. In this work we…
Performance Evaluation of Learned 3D Features
Riccardo Spezialetti, Samuele Salti, Luigi Di Stefano
Matching surfaces is a challenging 3D Computer Vision problem typically addressed by local features. Although a variety of 3D feature detectors and descriptors has been proposed in…
Unsupervised Domain Adaptation for Depth Prediction from Images
Alessio Tonioni, Matteo Poggi, Stefano Mattoccia +1
State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop…
Learning to Adapt for Stereo
Alessio Tonioni, Oscar Rahnama, Thomas Joy +3
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are succe…
Learning Across Tasks and Domains
Pierluigi Zama Ramirez, Alessio Tonioni, Samuele Salti +1
Recent works have proven that many relevant visual tasks are closely related one to another. Yet, this connection is seldom deployed in practice due to the lack of practical method…