no code implementations • 20 Sep 2022 • Thorbjørn Mosekjær Iversen, Rasmus Laurvig Haugaard, Anders Glent Buch
However, a single estimate is unable to express visual ambiguity, which in many cases is unavoidable due to object symmetries or occlusion of identifying features.
no code implementations • 2 Mar 2022 • Frederik Hagelskjaer, Anders Glent Buch
The use of synthetic training data avoids this data collection problem, but a configuration of the training procedure is necessary to overcome the domain gap problem.
no code implementations • CVPR 2022 • Rasmus Laurvig Haugaard, Anders Glent Buch
We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry.
no code implementations • 17 Nov 2020 • Frederik Hagelskjaer, Anders Glent Buch
While the use of synthetic training data prevents the need for manual annotation, there is currently a large performance gap between methods trained on real and synthetic data.
no code implementations • 19 Dec 2019 • Frederik Hagelskjær, Anders Glent Buch
We present a learning-based method for 6 DoF pose estimation of rigid objects in point cloud data.
1 code implementation • ECCV 2018 • Tomas Hodan, Frank Michel, Eric Brachmann, Wadim Kehl, Anders Glent Buch, Dirk Kraft, Bertram Drost, Joel Vidal, Stephan Ihrke, Xenophon Zabulis, Caner Sahin, Fabian Manhardt, Federico Tombari, Tae-Kyun Kim, Jiri Matas, Carsten Rother
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image.
no code implementations • ICCV 2017 • Anders Glent Buch, Lilita Kiforenko, Dirk Kraft
The key insight of our work is that a single correspondence between oriented points on the two models is constrained to cast votes in a 1 DoF rotational subgroup of the full group of poses, SE(3).
no code implementations • 23 Aug 2017 • Anders Glent Buch, Dirk Kraft, Joni-Kristian Kamarainen, Henrik Gordon Petersen, Norbert Krüger
We address the problem of estimating the alignment pose between two models using structure-specific local descriptors.
no code implementations • CVPR 2014 • Anders Glent Buch, Yang Yang, Norbert Krüger, Henrik Gordon Petersen
The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast.