Video super-resolution using an adaptive superpixel-guided auto-regressive model. (March 2016)

• Record Type: Journal Article
• Authors: Li, Kun; Zhu, Yanming; Yang, Jingyu; Jiang, Jianmin
• Is Part Of: Pattern recognition. Volume 51(2016:Mar.)
• Page Start: 59
• Page End: 71
• Publication Date: 2016-03
• Subjects: Video super-resolution -- Superpixel -- Auto-regressive model -- Spatio-temporal correlation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.08.008
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: This paper proposes a video super-resolution method based on an adaptive superpixel-guided auto-regressive (AR) model. Key-frames are automatically selected and super-resolved by a sparse regression method. Non-key-frames are super-resolved by exploiting the spatio-temporal correlations: the temporal correlation is exploited by an optical flow method while the spatial correlation is modeled by a superpixel-guided AR model. Experimental results show that the proposed method outperforms state-of-the-art methods in terms of both subjective visual quality and objective peak signal-to-noise ratio (PSNR). The proposed method requires less computation and is suitable for practical applications. Abstract : Highlights: An automatic key-frame selection method is proposed. An adaptive superpixel-guided auto-regressive (AR) model is proposed. Our method has the best visual quality and the highest PSNR. Our method requires less computation and is suitable for practical applications.