Real time super resolution reconstruction for video stream based on GPU

This paper proposes an efficient and structure-based image/video (interframe independent) super resolution (SR) scheme. Image/video SR is currently a very active area of research because it is used in various applications. The basic idea of the proposed scheme is based on the concepts of pattern redundancy and parallel computing. Global and local motions of pixels are well estimated by exploiting the repeated and structured patterns existing in the most nature images. The value of a missing pixel in the desired high resolution image is obtained by calculating the weighted average of the selected pixels according to the estimated motions, which is able to preserve the intrinsic geometric structure of the original low resolution image/video stream. After that, the estimated pixels' values will be re-corrected by using iterative back projection (IBP) approach in which auxiliary high frequency information embedded. The proposed scheme is mainly implemented in parallel programming strategy based on Compute Unified Device Architecture (CUDA), to reconstruct desired high resolution image/video steam from its low resolution counterparts. Experimental results show that the proposed method has high performance on both the visual quality and real time processing speed.