This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Regressor Basis Learning for Anchored Super-Resolution

Eirikur Agustsson and Radu Timofte and Luc Van Gool
23rd International Conference on Pattern Recognition (ICPR 2016)
December 2016


A+ aka Adjusted Anchored Neighborhood Regression - is a state-of-the-art method for exemplar-based single image super-resolution with low time complexity at both train and test time. By robustly training a clustered regression model over a low-resolution dictionary, its performance keeps improving with the dictionary size - even when using tens of thousands of regressors. However, this can pose a memory issue where the model size can grow to more than a gigabyte, limiting applicability in memory constrained scenarios. To address this, we propose Regressor Basis Learning (RB), a novel variant of A+ where we restrict the regressor set to a learned low-dimensional subspace, such that each regressor is coded as a linear combination of few basis regressors. We learn the regressor basis by alternating between closed form solutions of the optimal coding of the regressor set (given the basis) and the optimal regressor basis (given the coding). We validate RB on several standard benchmarks and achieve comparable performance to A+ but by using orders of magnitude fewer basis regressors, ie. 32 basis regressors instead of 1024 regressors. This makes our RB method ideal for memory constrained applications.

Download in pdf format
  author = {Eirikur Agustsson and Radu Timofte and Luc Van Gool},
  title = {Regressor Basis Learning for Anchored Super-Resolution},
  booktitle = {23rd International Conference on Pattern Recognition (ICPR 2016)},
  year = {2016},
  month = {December},
  keywords = {}