105 citations · 652 across the 49 of their papers we have counts for
5 papers · 1 filter
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
Christian Rupprecht, Iro Laina, Robert DiPietro +4
Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. I…
Hands-Free Segmentation of Medical Volumes via Binary Inputs
Florian Dubost, Loic Peter, Christian Rupprecht +2
We propose a novel hands-free method to interactively segment 3D medical volumes. In our scenario, a human user progressively segments an organ by answering a series of questions o…
Deep Active Contours
Christian Rupprecht, Elizabeth Huaroc, Maximilian Baust +1
We propose a method for interactive boundary extraction which combines a deep, patch-based representation with an active contour framework. We train a class-specific convolutional…
A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks
Felix Grün, Christian Rupprecht, Nassir Navab +1
Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging…
Deeper Depth Prediction with Fully Convolutional Residual Networks
Iro Laina, Christian Rupprecht, Vasileios Belagiannis +2
This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to…