Progressive Fusion for Unsupervised BinocularDepth Estimation using Cycled Networks (TPAMI)

Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need …

Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation (CVPR 2019)

Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need …

DeepGUM presented at ECCV 2018

Our paper on robust regression was presented at ECCV’18 in Munich [1]. This paper presents a methodological framework for robust regression combining the representation power of deep architectures with the outlier detection capabilities of probabilistic models, in particular of a Gaussian-Uniform mixture (GUM). The code is available at https://github.com/Stephlat/DeepGUM. Abstract: In this paper we address the problem …

Audio-Visual Gaze Control

This project introduces a novel neural network-based reinforcement learning approach for robot gaze control. Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of external sensors nor with human supervision. The robot learns to focus its attention onto groups of people from its …

Deep Mixture of Linear Inverse Regressions (CVPR 2017)

Convolutional Neural Networks (ConvNets) have become the state-of-the-art for many classification and regression problems in computer vision. When it comes to regression, approaches such as measuring the Euclidean distance of target and predictions are often employed as output layer. In this paper, we propose the coupling of a Gaussian mixture of linear inverse regressions with …