Jie Wu's paper, titled as “MULTIPLE-IMAGE SUPER RESOLUTION USING BOTH RECONSTRUCTION OPTIMIZATION AND DEEP NEURAL NETWORK”, was accepted by the IEEE Global Conference on Signal and Information Processing (GlobalSIP) which is a flagship conference of the IEEE Signal Processing Society. GlobalSIP'17 will be held in Montreal, Quebec, Canada on November 14-16, 2017. The conference focuses on signal and information processing with an emphasis on up-and-coming signal processing themes.
This paper presents an efficient multi-image super resolution (MISR) method. This novel solution consists of a L1-norm optimized reconstruction scheme for super resolution (SR), and a three layer convolutional network for artifacts removal, in a concatenated fashion. Such a two-stage method achieves excellent performance, which outperforms the existing state-of-the-art SR methods in both subjective and objective measurements (e.g., 5 to 7 dB improvements on popular image database using Peak Signal to Noise Ratio metric).