Super-resolution Using Constrained Deep Texture Synthesis
arXiv: Computer Vision and Pattern Recognition, Volume abs/1701.07604, 2017.
Hallucinating high frequency image details in single image super-resolution is a challenging task. Traditional super-resolution methods tend to produce oversmoothed output images due to the ambiguity in mapping between low and high resolution patches. We build on recent success in deep learning based texture synthesis and show that this r...More
Full Text (Upload PDF)