Accelerating super-resolution for 4K upscaling
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessRestricted access - publisher's policy
This paper presents a fast Super-Resolution (SR) algorithm based on a selective patch processing. Motivated by the observation that some regions of images are smooth and unfocused and can be properly upscaled with fast interpolation methods, we locally estimate the probability of performing a degradation-free upscaling. Our proposed framework explores the usage of supervised machine learning techniques and tackles the problem using binary boosted tree classifiers. The applied upscaler is chosen based on the obtained probabilities: (1) A fast upscaler (e.g. bicubic interpolation) for those regions which are smooth or (2) a linear regression SR algorithm for those which are ill-posed. The proposed strategy accelerates SR by only processing the regions which benefit from it, thus not compromising quality. Furthermore all the algorithms composing the pipeline are naturally parallelizable and further speed-ups could be obtained.
CitationPérez-Pellitero, E., Salvador, J., Ruiz-Hidalgo, J., Rosenhahn, B. Accelerating super-resolution for 4K upscaling. A: International Conference on Consumer Electronics. "2015 IEEE International Conference on Consumer Electronics (ICCE 2015): Las Vegas, Nevada, USA: 9-12 January 2015". Las Vegas, Nevada: Institute of Electrical and Electronics Engineers (IEEE), 2015, p. 317-320.
|cPerez-Pellitero15.pdf||Postprint article principal||1,074Mb||Restricted access|