Face restoration is important in face image processing, and has been widely studied in recent years. However, previous works often fail to generate plausible high quality (HQ) results for real-world low quality (LQ) face images. In this paper, we propose a new progressive semantic-aware style transformation framework, named PSFR-GAN, for face restoration. Specifically, instead of using an encoder-decoder framework as previous methods, we formulate the restoration of LQ face images as a multi-scale progressive restoration procedure through semantic-aware style transformation. Given a pair of LQ face image and its corresponding parsing map, we first generate a multi-scale pyramid of the inputs, and then progressively modulate different scale features from coarse-to-fine in a semantic-aware style transfer way. Compared with previous networks, the proposed PSFR-GAN makes full use of the semantic (parsing maps) and pixel (LQ images) space information from different scales of input pairs. In addition, we further introduce a semantic aware style loss which calculates the feature style loss for each semantic region individually to improve the details of face textures. Finally, we pretrain a face parsing network which can generate decent parsing maps from real-world LQ face images. Experiment results show that our model trained with synthetic data can not only produce more realistic high-resolution results for synthetic LQ inputs and but also generalize better to natural LQ face images compared with state-of-the-art methods. Codes are available at https://github.com/chaofengc/PSFRGAN.
Returns to education are traditionally estimated in a Mincer wage equation from the variation in schooling for a cross-section of individuals of different ages. Because individuals receive education at different time periods, when the quality of their education may not be identical, this method leads to an overor underestimation of the return to education of a given quality depending on how education quality evolves over time. This quality issue interacts with ability bias from self-selection into schooling and is particularly problematic when comparing returns across different countries. Using microdata from the International Adult Literacy Survey, we construct quality adjusted measures of schooling attained at different time periods and use these along with international literacy test information to estimate returns to skills for 13 countries. Estimated returns to quality-adjusted education are considerably higher than the traditional estimate for most countries, but these are offset to varying degrees by selection biases on ability. The combined corrections alter significantly the pattern of returns to schooling and skill seen from naïve Mincer wage equations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.