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

Titel:: What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
Dokumenttyp:: Zeitschriftenaufsatz
Autor(en):: Mayer, Nikolaus; Ilg, Eddy; Fischer, Philipp; Hazirbas, Caner; Cremers, Daniel; Dosovitskiy, Alexey; Brox, Thomas
Zeitschriftentitel:: arXiv
Jahr:: 2018
Volltext / DOI:: doi:10.48550/ARXIV.1801.06397
Verlag / Institution:: arXiv
Publikationsdatum:: 01.01.2018
BibTeX