Výsledky vyhledávání - "Mikhail Usvyatsov"

PREDATOR: Registration of 3D Point Clouds with Low Overlap

Autor: Andreas Wieser, Konrad Schindler, Zan Gojcic, Shengyu Huang, Mikhail Usvyatsov

Publikováno v: CVPR

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b67b37470a2f322706167feb79fa56e
https://doi.org/10.1109/cvpr46437.2021.00425

Zobrazit plný text záznamu

Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation

Autor: Mikhail Usvyatsov, Anastasia Makarova, Rafael Ballester-Ripoll, Maxim Rakhuba, Andreas Krause, Konrad Schindler

Publikováno v: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

We propose an end-to-end trainable framework that processes large-scale visual data tensors by looking at a fraction of their entries only. Our method combines a neural network encoder with a tensor train decomposition to learn a low-rank latent enco

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14da65400bfb65d265da5ed4e3214a2d

Zobrazit plný text záznamu

Indoor Scene Recognition in 3D

Autor: Konrad Schindler, Shengyu Huang, Mikhail Usvyatsov

Publikováno v: IROS

Recognising in what type of environment one is located is an important perception task. For instance, for a robot operating in indoors it is helpful to be aware whether it is in a kitchen, a hallway or a bedroom. Existing approaches attempt to classi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::950b00055ba991396dde85c97c4bfd94
http://arxiv.org/abs/2002.12819

Zobrazit plný text záznamu

Visual recognition in the wild by sampling deep similarity functions

Autor: Konrad Schindler, Mikhail Usvyatsov

Publikováno v: ICRA

Recognising relevant objects or object states in its environment is a basic capability for an autonomous robot. The dominant approach to object recognition in images and range images is classification by supervised machine learning, nowadays mostly w

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e6231500f54a7d8505ca5636bd2309b

Zobrazit plný text záznamu

Inference, learning and attention mechanisms that exploit and preserve sparsity in CNNs

Autor: Konrad Schindler, Silvano Galliani, Mikhail Usvyatsov, Timo Hackel, Jan Dirk Wegner

Publikováno v: Pattern Recognition
Lecture Notes in Computer Science ISBN: 9783030129385
GCPR

Pattern Recognition
ISBN:978-3-030-12938-5
ISBN:978-3-030-12939-2

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc6fc2cfc1e0d4c9761a2e75911e75ee

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání