Fast super-resolution via dense local training and inverse regressor search
10.1007/978-3-319-16811-1_23
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/27529
Tipus de documentArticle
Data publicació2014-11-01
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Regression-based Super-Resolution (SR) addresses the upscaling problem by learning a mapping function (i.e. regressor) from the low-resolution to the high-resolution manifold. Under the locally linear assumption, this complex non-linear mapping can be properly modeled by a set of linear regressors distributed across the manifold. In such methods, most of the testing time is spent searching for the right regressor within this trained set. In this paper we propose a novel inverse-search approach for regression-based SR. Instead of performing a search from the image to the dictionary of regressors, the search is done inversely from the regressors’ dictionary to the image patches. We approximate this framework by applying spherical hashing to both image and regressors, which reduces the inverse search into computing a trained function. Additionally, we propose an improved training scheme for SR linear regressors which improves perceived and objective quality. By merging both contributions we improve speed and quality compared to the state-of-the-art.
CitacióPérez-Pellitero, E. [et al.]. Fast super-resolution via dense local training and inverse regressor search. "Lecture notes in computer science", 01 Novembre 2014, p. 346-359.
ISSN0302-9743
Versió de l'editorhttp://link.springer.com/chapter/10.1007%2F978-3-319-16811-1_23
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
Fast super-reso ... verse regressor search.pdf | 19,07Mb | Visualitza/Obre |