Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Peter V. Gehler"'
Autor:
Ghalia Hemrit, Simone Bianco, Brian V. Funt, Lilong Shi, Peter V. Gehler, Graham D. Finlayson, Mark S. Drew, Arjan Gijsenij
The ColorChecker dataset is one of the most widely used image sets for evaluating and ranking illuminant estimation algorithms. However, this single set of images has at least 3 different sets of ground-truth (i.e., correct answers) associated with i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb493cfbe9cf8f441fd57bb6fd270316
http://hdl.handle.net/10281/255406
http://hdl.handle.net/10281/255406
Publikováno v:
ICCV
Today, a frame-based camera is the sensor of choice for machine vision applications. However, these cameras, originally developed for acquisition of static images rather than for sensing of dynamic uncontrolled visual environments, suffer from high p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da647c2f78896c7899bc5a622c142b8e
https://doi.org/10.1109/iccv.2019.00161
https://doi.org/10.1109/iccv.2019.00161
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030336752
GCPR
GCPR
Dense prediction tasks typically employ encoder-decoder architectures, but the prevalent convolutions in the decoder are not image-adaptive and can lead to boundary artifacts. Different generalized convolution operations have been introduced to count
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::845c0c07e22689d92dd1e49a6d6acdeb
https://doi.org/10.1007/978-3-030-33676-9_24
https://doi.org/10.1007/978-3-030-33676-9_24
Publikováno v:
3DV
Direct prediction of 3D body pose and shape parameters remains a challenge even for highly parameterized, deep learning models. The representation of the prediction space is difficult to map to from the plain 2D image space, perspective ambiguities m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f78899cfef5e9b33addae2992cf8bd8
https://doi.org/10.1109/3dv.2018.00062
https://doi.org/10.1109/3dv.2018.00062
Autor:
Arjan Gijsenij, Brian V. Funt, Simone Bianco, Peter V. Gehler, Ghalia Hemrit, Lilong Shi, Graham D. Finlayson, Mark S. Drew
In a previous work, it was shown that there is a curious problem with the benchmark ColorChecker dataset for illuminant estimation. To wit, this dataset has at least 3 different sets of ground-truths. Typically, for a single algorithm a single ground
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2aafb512b988f46058d66998f67fa25a
http://arxiv.org/abs/1805.12262
http://arxiv.org/abs/1805.12262
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012397
ECCV (9)
ECCV (9)
Modern deep learning systems successfully solve many perception tasks such as object pose estimation when the input image is of high quality. However, in challenging imaging conditions such as on low resolution images or when the image is corrupted b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::040470483ed696639c47d619042a5f74
https://doi.org/10.1007/978-3-030-01240-3_33
https://doi.org/10.1007/978-3-030-01240-3_33
Publikováno v:
Computer Vision and Image Understanding. 136:32-44
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image format
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17ad170fd82bff7cbc26f9c004404293
https://doi.org/10.1016/j.cviu.2015.03.002
https://doi.org/10.1016/j.cviu.2015.03.002
Publikováno v:
ICCV
In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very little extra computational cost.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2871e1ed2de4f5d1682c87d5404299e4
https://doi.org/10.1109/iccv.2017.477
https://doi.org/10.1109/iccv.2017.477
Autor:
Yinghao Huang, Federica Bogo, Christoph Lassner, Angjoo Kanazawa, Peter V. Gehler, Javier Romero, Ijaz Akhter, Michael J. Black
Publikováno v:
3DV
Existing markerless motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, limiting their application scenarios. Here we present a fully automatic method that, given multi-view videos, estimates 3D
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44731af8e006ff0c90d99639e1649b6f
https://doi.org/10.1109/3dv.2017.00055
https://doi.org/10.1109/3dv.2017.00055
Publikováno v:
CVPR
We propose a technique that propagates information forward through video data. The method is conceptually simple and can be applied to tasks that require the propagation of structured information, such as semantic labels, based on video content. We p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf8fa5b53dabcf5bee5e517be5299c17
https://doi.org/10.1109/cvpr.2017.336
https://doi.org/10.1109/cvpr.2017.336