Supervised Deep Kriging for Single-Image Super-Resolution
This work addresses image super-resolution for computer vision applications, offering a statistically interpretable deep learning method, though it is incremental as it combines existing techniques.
The authors tackled single-image super-resolution by integrating kriging, a geostatistical interpolation method, with deep learning to create a supervised approach that generates kriging weights via a network, achieving competitive results with state-of-the-art methods and enabling bias and variance estimation.
We propose a novel single-image super-resolution approach based on the geostatistical method of kriging. Kriging is a zero-bias minimum-variance estimator that performs spatial interpolation based on a weighted average of known observations. Rather than solving for the kriging weights via the traditional method of inverting covariance matrices, we propose a supervised form in which we learn a deep network to generate said weights. We combine the kriging weight generation and kriging process into a joint network that can be learned end-to-end. Our network achieves competitive super-resolution results as other state-of-the-art methods. In addition, since the super-resolution process follows a known statistical framework, we are able to estimate bias and variance, something which is rarely possible for other deep networks.