Zobrazeno 1 - 10 of 37 pro vyhledávání: '"Hanno Ackermann"'
1
Multilinear Modelling of Faces and Expressions
Autor: Sami S. Brandt, Hanno Ackermann, Stella Grasshof, Jörn Ostermann
Publikováno v: Grasshof, S, Ackermann, H, Brandt, S S & Ostermann, J 2021, ' Multilinear Modelling of Faces and Expressions ', I E E E Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3540-3554 . https://doi.org/10.1109/TPAMI.2020.2986496
In this work, we present a new versatile 3D multilinear statistical face model, based on a tensor factorisation of 3D face scans, that decomposes the shapes into person and expression subspaces. Investigation of the expression subspace reveals an inh
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66ff8f8446ad494795811c2c2da8cd88
https://pure.itu.dk/portal/da/publications/7aabbc12-7aeb-4bc2-8472-de92e1b3d9cd
Zobrazit plný text záznamu
2
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
Autor: Eric Brachmann, Michael Ying Yang, Hanno Ackermann, Bodo Rosenhahn, Florian Kluger
Publikováno v: CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13065-13074
STARTPAGE=13065;ENDPAGE=13074;TITLE=2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring these primitives is an important
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3919075a1d82edc3b87ea8222ad0f9f2
http://arxiv.org/abs/2105.02047
Zobrazit plný text záznamu
4
CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus
Autor: Carsten Rother, Florian Kluger, Eric Brachmann, Hanno Ackermann, Bodo Rosenhahn, Michael Ying Yang
Publikováno v: CVPR
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4633-4642
STARTPAGE=4633;ENDPAGE=4642;TITLE=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. Applications include finding multiple vanishing points in man-made scenes, fitting planes to architectural imagery, or estimating multiple ri
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36dc7818b14d513b19eaad3c795cfce6
https://doi.org/10.1109/cvpr42600.2020.00469
Zobrazit plný text záznamu
5
Temporally Consistent Horizon Lines
Autor: Hanno Ackermann, Bodo Rosenhahn, Florian Kluger, Michael Ying Yang
Publikováno v: ICRA
arXiv.org, 1-16. Cornell University
STARTPAGE=1;ENDPAGE=16;TITLE=arXiv.org
2020 IEEE International Conference on Robotics and Automation, ICRA 2020, 3161-3167
STARTPAGE=3161;ENDPAGE=3167;TITLE=2020 IEEE International Conference on Robotics and Automation, ICRA 2020
The horizon line is an important geometric feature for many image processing and scene understanding tasks in computer vision. For instance, in navigation of autonomous vehicles or driver assistance, it can be used to improve 3D reconstruction as wel
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85ec133bdb4731c5a010565b78520ba3
https://doi.org/10.1109/icra40945.2020.9197170
Zobrazit plný text záznamu
7
Learning Disentangled Representations via Independent Subspaces
Autor: Hanno Ackermann, Bodo Rosenhahn, Maren Awiszus
Publikováno v: ICCV Workshops
Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for l
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::927cdf63159de5ad0c35dcfba9d948d3
https://doi.org/10.1109/iccvw.2019.00069
Zobrazit plný text záznamu
9
A Kinematic Chain Space for Monocular Motion Capture
Autor: Bastian Wandt, Hanno Ackermann, Bodo Rosenhahn
Publikováno v: Lecture Notes in Computer Science ISBN: 9783030110178
ECCV Workshops (4)
This paper deals with motion capture of kinematic chains (e.g. human skeletons) from monocular image sequences taken by uncalibrated cameras. We present a method based on projecting an observation onto a kinematic chain space (KCS). An optimization o
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::292c617d6510210f65227cf8b0550a90
https://doi.org/10.1007/978-3-030-11018-5_4
Zobrazit plný text záznamu
10
Region-based Cycle-Consistent Data Augmentation for Object Detection
Autor: Christoph Reinders, Bastian Wandt, Hanno Ackermann, Philipp Schelske, Kevin Raetz, Florian Kluger, Bodo Rosenhahn
Publikováno v: IEEE BigData
Roads constitute a major part of the lives of everybody. Heavy use, for instance by cars and especially trucks, and even soil movement lead to visible damages. While major roads are regularly inspected, smaller roads often lack attention. It is there
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::afa96c4b08cb366c7e4e0d2a804be23a
https://doi.org/10.1109/bigdata.2018.8622318
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje