12 citations · 25 across the 5 of their papers we have counts for
5 papers
ConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particles
Max Coenen, Tobias Schack, Dries Beyer +2
We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelle…
Learning to Sieve: Prediction of Grading Curves from Images of Concrete Aggregate
Max Coenen, Dries Beyer, Christian Heipke +1
A large component of the building material concrete consists of aggregate with varying particle sizes between 0.125 and 32 mm. Its actual size distribution significantly affects th…
Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior
Max Coenen, Franz Rottensteiner
The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse…
Semi-Supervised Segmentation of Concrete Aggregate Using Consensus Regularisation and Prior Guidance
Max Coenen, Tobias Schack, Dries Beyer +2
In order to leverage and profit from unlabelled data, semi-supervised frameworks for semantic segmentation based on consistency training have been proven to be powerful tools to si…
Probabilistic Vehicle Reconstruction Using a Multi-Task CNN
Max Coenen, Franz Rottensteiner
The retrieval of the 3D pose and shape of objects from images is an ill-posed problem. A common way to object reconstruction is to match entities such as keypoints, edges, or conto…