Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Martin Sundermeyer"'
Publikováno v:
ICRA
We present a novel framework for self-supervised grasped object segmentation with a robotic manipulator. Our method successively learns an agnostic foreground segmentation followed by a distinction between manipulator and object solely by observing t
We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83afcae83b7cf06761b7cda722c64d01
https://elib.dlr.de/135549/
https://elib.dlr.de/135549/
Autor:
Frank Michel, Jiří Matas, Carsten Rother, Bertram Drost, Yann Labbé, Martin Sundermeyer, Eric Brachmann, Tomáš Hodaň
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
ECCV Workshops (2)
This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB-D im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6bf28b4402c3de7667c498313e002187
https://doi.org/10.1007/978-3-030-66096-3_39
https://doi.org/10.1007/978-3-030-66096-3_39
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012304
ECCV (6)
ECCV (6)
We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c42a72c543b6472507aad337944908db
http://arxiv.org/abs/1902.01275
http://arxiv.org/abs/1902.01275
Autor:
Zoltan-Csaba Marton, Narunas Vaskevicius, Martin Sundermeyer, En Yen Puang, Maximilian Durner, Rudolph Triebel, Kai O. Arras
Publikováno v:
CVPR
We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during training, b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9fc504c110a16827e1d2ea523cf141d
Autor:
Martin Sundermeyer, Maximilian Durner, Ferenc Balint-Benczedi, Rudolph Triebel, Manuel Brucker, Zoltan-Csaba Marton
Publikováno v:
Springer Proceedings in Advanced Robotics ISBN: 9783030339494
ISER
ISER
We present a perception system for mobile manipulation tasks. The primary design goal of the proposed system is to minimize human interaction during system setup which is achieved by several means, such as automatic training data generation, the use
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4045dc5f7eea510b005d0eaba2fe80f
https://elib.dlr.de/122686/
https://elib.dlr.de/122686/
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 23:517-529
Language models have traditionally been estimated based on relative frequencies, using count statistics that can be extracted from huge amounts of text data. More recently, it has been found that neural networks are particularly powerful at estimatin
Publikováno v:
INTERSPEECH
In this paper, we investigated various word clustering methods, by studying two clustering algorithms: Brown clustering and exchange algorithm, and three objective functions derived from different class-based language models (CBLM): two-sided, predic
Publikováno v:
INTERSPEECH
Scopus-Elsevier
Scopus-Elsevier
We present a novel toolkit that implements the long short-term memory (LSTM) neural network concept for language modeling. The main goal is to provide a software which is easy to use, and which allows fast training of standard recurrent and LSTM neur
Publikováno v:
EMNLP
This work presents two different translation models using recurrent neural networks. The first one is a word-based approach using word alignments. Second, we present phrase-based translation models that are more consistent with phrasebased decoding.