activity
20152017
most citedLearning the Matching Function

18 citations · 22 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV2017

An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation

Christian F. Baumgartner, Lisa M. Koch, Marc Pollefeys +1

Accurate segmentation of the heart is an important step towards evaluating cardiac function. In this paper, we present a fully automated framework for segmentation of the left (LV)…

cs.CV20174 cited

3D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detection

Christian Häne, Lionel Heng, Gim Hee Lee +4

Cameras are a crucial exteroceptive sensor for self-driving cars as they are low-cost and small, provide appearance information about the environment, and work in various weather c…

cs.CV2017

Slanted Stixels: Representing San Francisco's Steepest Streets

Daniel Hernandez-Juarez, Lukas Schneider, Antonio Espinosa +5

In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive…

cs.CV2017

Semantically Informed Multiview Surface Refinement

Maros Blaha, Mathias Rothermel, Martin R. Oswald +5

We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes. Our method alternates between updating the shape and the semantic labels. In the…

cs.CV2017

Matching neural paths: transfer from recognition to correspondence search

Nikolay Savinov, Lubor Ladicky, Marc Pollefeys

Many machine learning tasks require finding per-part correspondences between objects. In this work we focus on low-level correspondences - a highly ambiguous matching problem. We p…

cs.CV2016

Automatic 3D Reconstruction of Manifold Meshes via Delaunay Triangulation and Mesh Sweeping

Andrea Romanoni, Amaël Delaunoy, Marc Pollefeys +1

In this paper we propose a new approach to incrementally initialize a manifold surface for automatic 3D reconstruction from images. More precisely we focus on the automatic initial…