You're currently viewing an old version of this dataset. To see the current version, click here.

Deep Depth From Focus

Depth from focus (DFF) is a highly ill-posed inverse problem because the optimal focal distance is inferred from sharpness measures which fail in untextured areas. Existing variational solutions revert to spatial regularization to fill in the missing depth, which are not generalized to more complex geometric environments.

Data and Resources

Cite this as

Caner Hazirbas, Sebastian Georg Soyer, Maximilian Christian Staab, Laura Leal-Taixe, Daniel Cremers (2024). Dataset: Deep Depth From Focus. https://doi.org/10.57702/4yen14xf

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.1704.01085
Author Caner Hazirbas
More Authors
Sebastian Georg Soyer
Maximilian Christian Staab
Laura Leal-Taixe
Daniel Cremers
Homepage https://vision.cs.tum.edu/data/datasets/ddff12scene