Share Email Print
cover

Proceedings Paper

Robust video super-resolution with registration efficiency adaptation
Author(s): Xinfeng Zhang; Ruiqin Xiong; Siwei Ma; Li Zhang; Wen Gao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Super-Resolution (SR) is a technique to construct a high-resolution (HR) frame by fusing a group of low-resolution (LR) frames describing the same scene. The effectiveness of the conventional super-resolution techniques, when applied on video sequences, strongly relies on the efficiency of motion alignment achieved by image registration. Unfortunately, such efficiency is limited by the motion complexity in the video and the capability of adopted motion model. In image regions with severe registration errors, annoying artifacts usually appear in the produced super-resolution video. This paper proposes a robust video super-resolution technique that adapts itself to the spatially-varying registration efficiency. The reliability of each reference pixel is measured by the corresponding registration error and incorporated into the optimization objective function of SR reconstruction. This makes the SR reconstruction highly immune to the registration errors, as outliers with higher registration errors are assigned lower weights in the objective function. In particular, we carefully design a mechanism to assign weights according to registration errors. The proposed superresolution scheme has been tested with various video sequences and experimental results clearly demonstrate the effectiveness of the proposed method.

Paper Details

Date Published: 5 August 2010
PDF: 8 pages
Proc. SPIE 7744, Visual Communications and Image Processing 2010, 774432 (5 August 2010); doi: 10.1117/12.863370
Show Author Affiliations
Xinfeng Zhang, Institute of Computing Technology (China)
Ruiqin Xiong, Peking Univ. (China)
Siwei Ma, Peking Univ. (China)
Li Zhang, Peking Univ. (China)
Wen Gao, Peking Univ. (China)


Published in SPIE Proceedings Vol. 7744:
Visual Communications and Image Processing 2010
Pascal Frossard; Houqiang Li; Feng Wu; Bernd Girod; Shipeng Li; Guo Wei, Editor(s)

© SPIE. Terms of Use
Back to Top