UHD Video Super-Resolution Using Low-Rank and Sparse Decomposition

Salehe Erfanian Ebadi, Valia Guerra Ones, Ebroul Izquierdo; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1889-1897

Abstract


Sparse coding-based algorithms have been successfully applied to the single-image super resolution problem. Conventional multi-image SR algorithms incorporate auxiliary frames into the model by a registration process using subpixel block matching algorithms that are computationally expensive. This becomes increasingly important as super-resolving UHD video content with existing sparse-based SR approaches become less efficient. In order to fully utilize the spatio-temporal information, we propose a novel multi-frame video SR approach that is aided by a low-rank plus sparse decomposition of the video sequence. We introduce a group of pictures structure where we seek a rank-1 low-rank part that recovers the shared spatio-temporal information among the frames in the GOP. Then we super-resolve the low-rank frame and sparse frames separately. This assumption results in significant time reductions, as well as surpassing state-of-the-art performance both qualitatively and quantitatively.

Related Material


[pdf]
[bibtex]
@InProceedings{Ebadi_2017_ICCV,
author = {Erfanian Ebadi, Salehe and Guerra Ones, Valia and Izquierdo, Ebroul},
title = {UHD Video Super-Resolution Using Low-Rank and Sparse Decomposition},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}