Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Daniel, Kondermann"'
Publikováno v:
Image Processing On Line, Vol 3, Pp 151-172 (2013)
The seminal work of Horn and Schunck is the first variational method for optical flow estimation. It introduced a novel framework where the optical flow is computed as the solution of a minimization problem. From the assumption that pixel intensities
Externí odkaz:
https://doaj.org/article/79055786741441e6a59e2fb218693dc3
Publikováno v:
International Journal of Computer Vision. 129:2029-2030
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94980743020767358186dd83c3b0cdc8
https://doi.org/10.1007/s11263-021-01455-x
https://doi.org/10.1007/s11263-021-01455-x
Publikováno v:
International Journal of Computer Assisted Radiology and Surgery. 12:161-166
With the recent trend toward big data analysis, neuroimaging datasets have grown substantially in the past years. While larger datasets potentially offer important insights for medical research, one major bottleneck is the requirement for resources o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1e7365daacc4b4dabe34ccb20673aae
https://doi.org/10.1007/s11548-016-1445-9
https://doi.org/10.1007/s11548-016-1445-9
Publikováno v:
Image Processing On Line, Vol 3, Pp 151-172 (2013)
The seminal work of Horn and Schunck is the first variational method for optical flow estimation. It introduced a novel framework where the optical flow is computed as the solution of a minimization problem. From the assumption that pixel intensities
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a08adb1cafa8a6674f5d8166e593dd1c
http://www.ipol.im/pub/art/2013/20/
http://www.ipol.im/pub/art/2013/20/
Publikováno v:
Computer Vision – ACCV 2016 ISBN: 9783319541860
ACCV (3)
ACCV (3)
In computer vision communities such as stereo, optical flow, or visual tracking, commonly accepted and widely used benchmarks have enabled objective comparison and boosted scientific progress.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5bbb70a4d233d0c9835318a79369bb03
https://doi.org/10.1007/978-3-319-54187-7_2
https://doi.org/10.1007/978-3-319-54187-7_2
Autor:
Mohsen Rahimimoghaddam, Jonas Andrulis, Daniel Kondermann, Katrin Honauer, Bernd Jähne, Alexander Brock, Karsten Krispin, Rahul Nair, Claus Brenner, Sabine Hofmann, Burkhard Gussefeld
Publikováno v:
CVPR Workshops
Recent advances in autonomous driving require more and more highly realistic reference data, even for difficult situations such as low light and bad weather. We present a new stereo and optical flow dataset to complement existing benchmarks. It was s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f89d9a8c2e34d42b7eade260c93a667
https://doi.org/10.1109/cvprw.2016.10
https://doi.org/10.1109/cvprw.2016.10
Publikováno v:
Advances in Visual Computing ISBN: 9783319508344
ISVC (1)
ISVC (1)
Optical flow ground truth generated by computer graphics has many advantages. For example, we can systematically vary scene parameters to understand algorithm sensitivities. But is synthetic ground truth realistic enough? Appropriate material models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::297aa8508632673c350903c368d6ab73
https://doi.org/10.1007/978-3-319-50835-1_8
https://doi.org/10.1007/978-3-319-50835-1_8
Publikováno v:
ICCV
Stereo reconstruction in presence of reality faces many challenges that still need to be addressed. This paper considers reflections, which introduce incorrect matches due to the observation violating the diffuse-world assumption underlying the major
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f2ced34cbfd29f66d9ddebbc8f13641
https://doi.org/10.1109/iccv.2015.264
https://doi.org/10.1109/iccv.2015.264
Publikováno v:
ICCV
Performance characterization of stereo methods is mandatory to decide which algorithm is useful for which application. Prevalent benchmarks mainly use the root mean squared error (RMS) with respect to ground truth disparity maps to quantify algorithm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::27b9ab12aeb1e971b7770386a5ba5894
https://doi.org/10.1109/iccv.2015.245
https://doi.org/10.1109/iccv.2015.245
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319249469
GCPR
GCPR
We present an approach for computing dense scene flow from two large displacement RGB-D images. When dealing with large displacements the crucial step is to estimate the overall motion correctly. While state-of-the-art approaches focus on RGB informa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::024062f2763a0f61a08374bf3f47387b
https://doi.org/10.1007/978-3-319-24947-6_23
https://doi.org/10.1007/978-3-319-24947-6_23