@inproceedings{0a58cb193a2b40f5a562541665d9b5f6,
title = "Deep learning of local RGB-D patches for 3D object detection and 6D pose estimation",
abstract = "We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collection of random local patches. During testing, scene patch descriptors are matched against a database of synthetic model view patches and cast 6D object votes which are subsequently filtered to refined hypotheses. We evaluate on three datasets to show that our method generalizes well to previously unseen input data, delivers robust detection results that compete with and surpass the state-of-the-art while being scalable in the number of objects.",
author = "Wadim Kehl and Fausto Milletari and Federico Tombari and Slobodan Ilic and Nassir Navab",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.; 14th European Conference on Computer Vision, ECCV 2016 ; Conference date: 08-10-2016 Through 16-10-2016",
year = "2016",
doi = "10.1007/978-3-319-46487-9_13",
language = "English",
isbn = "9783319464862",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "205--220",
editor = "Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling",
booktitle = "Computer Vision - 14th European Conference, ECCV 2016, Proceedings",
}