What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?

Mayer, Nikolaus; Ilg, Eddy; Fischer, Philipp; Hazirbas, Caner; Cremers, Daniel; Dosovitskiy, Alexey; Brox, Thomas

doi:10.48550/ARXIV.1801.06397

Title:: What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
Document type:: Zeitschriftenaufsatz
Author(s):: Mayer, Nikolaus; Ilg, Eddy; Fischer, Philipp; Hazirbas, Caner; Cremers, Daniel; Dosovitskiy, Alexey; Brox, Thomas
Journal title:: arXiv
Year:: 2018
Fulltext / DOI:: doi:10.48550/ARXIV.1801.06397
Publisher:: arXiv
Date of publication:: 01.01.2018
BibTeX