A Simple & Effective Video Sequence Super-Resolution Algorithm

To solve the problem of sequence to sequence super resolution, a video sequence super resolution algorithm based on a frame of reference high resolution image is proposed in this paper.The algorithm is based on the fact that in most cases, the vidicon device has dual mode:HR(High Resolution) still and LR(Low Resolution) video.In the algorithm, a HR still image acquired from the same scene is used as an example, the high frequency details of it are extracted and then motion compensated and reliability weighted for super resolution of the corresponding low resolution frames.The estimated HR frames are then constraint optimized under the Maximum A Posteriori(MAP) framework to improve its fidelity.Evaluated by several sequences, the proposed algorithm shows obvious performance improvements compared with the traditional bilinear interpolation and the MAP based static batch method.The average PSNR(Peak Signal-to-Noise Ratio) of the reconstructed frames are improved by more than 2.4 dB.