This paper proposes an adaptive video super-resolution (SR) method based on superpixel-guided auto-regressive (AR) model. The keyframes are automatically selected and super-resolved by a sparse regression method. The non-key-frames are super-resolved by simultaneously exploiting the spatiotemporal correlations: the temporal correlation is exploited by a GPU-based optical flow method while the spatial correlation is modelled by a superpixel-guided AR model. Experimental results show that the proposed method outperforms the existing benchmark in terms of both subjective visual quality and objective peak-to-peak signal-to-noise ratio (PSNR). At the same time, the running time of the proposed method is the shortest in comparison with the state-of-the-art methods, which makes the proposed method suitable for practical applications.
展开▼
