Face Hallucination Revisited: An Exploratory Study on Dataset Bias

no code implementations • 21 Dec 2018 • Klemen Grm, Martin Pernuš, Leo Cluzel, Walter Scheirer, Simon Dobrišek, Vitomir Štruc

This down-sampling (or degradation) procedure not only defines the characteristics of the LR training data, but also determines the type of image degradations the learned FH models are eventually able to handle.

Face Hallucination Hallucination