Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Maxim Tatarchenko"'
Publikováno v:
CVPR
Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training. Common approaches predominantly rely on learned global shape priors and, hence, disregard detailed local obse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e1b08442929798e89b632105415eb6c
http://arxiv.org/abs/2104.00476
http://arxiv.org/abs/2104.00476
Publikováno v:
IROS
We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of self-super
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce28ca0a7f36dcd4a36c5e236ffc36cd
http://arxiv.org/abs/1910.07948
http://arxiv.org/abs/1910.07948
Publikováno v:
ISBI
We present $\mathrm { ISOO } _ { \mathrm { DL } } ^ { \mathrm { V } 2 } -$ a method for semantic instance segmentation of touching and overlapping objects. We introduce a series of design modifications to the prior framework, including a novel mixed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f9d9f638d082d558ec2de599772015a
https://doi.org/10.1109/isbi.2019.8759334
https://doi.org/10.1109/isbi.2019.8759334
Publikováno v:
CVPR
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5d2dc7a4fd69d16dca0ec4d2d4a3d92a
Publikováno v:
CVPR
We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions - a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method operates d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::439618bc78b0aad90c7652726f329dda
https://doi.org/10.1109/cvpr.2018.00409
https://doi.org/10.1109/cvpr.2018.00409
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464770
ECCV (7)
ECCV (7)
We present a convolutional network capable of inferring a 3D representation of a previously unseen object given a single image of this object. Concretely, the network can predict an RGB image and a depth map of the object as seen from an arbitrary vi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0c7b343c391b5ab784808f82e8bba78
https://doi.org/10.1007/978-3-319-46478-7_20
https://doi.org/10.1007/978-3-319-46478-7_20
Publikováno v:
ICRA
Observing human activities can reveal a lot about the structure of the environment, the objects contained therein and also their functionality. This knowledge, in turn, can be useful for robots interacting with humans or for robots performing mobile
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7310ae81dfcf8193040dd1b1b7a63ac9
https://doi.org/10.1109/icra.2015.7139842
https://doi.org/10.1109/icra.2015.7139842
We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color. We train the networks on rendered 3D models of chairs, tables, and cars. Our experiments show that the netwo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b65697a1c29ae7b89441fd7006eae1e