A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution

• Published in: Computer Vision -- ACCV 2014 pp. 111 - 126
• Main Authors: Timofte, Radu, De Smet, Vincent, Van Gool, Luc
• Format: Book Chapter
• Language: English; Japanese
• Published: Cham Springer International Publishing 2015
• Series: Lecture Notes in Computer Science
• Subjects: Convolutional Neural Network; Dictionary Size; Neighborhood Size; Sparse Code; Training Sample
• ISBN: 3319168169; 9783319168166
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-16817-3_8

We address the problem of image upscaling in the form of single image super-resolution based on a dictionary of low- and high-resolution exemplars. Two recently proposed methods, Anchored Neighborhood Regression (ANR) and Simple Functions (SF), provide state-of-the-art quality performance. Moreover,...