论文信息 - 4K-HDTV super-resolution system

4K-HDTV super-resolution system

This paper proposes a super-resolution system for 4K-HDTV. In the basic super-resolution system, the input image is decomposed by the total variation filter into structure and texture components. The structure components are enhanced by the shock filter whereas the texture components are enhanced by the pulse enhancement filter. Two important additional functions are included in the proposed system: MPEG compression-noise removal and human face super-resolution processing. A GPU implementation that was also tested demonstrated that this system can be implemented for 4K-HDTV motion pictures.

[1] L. Rudin,et al. Feature-oriented image enhancement using shock filters , 1990 .

[2] Antonin Chambolle,et al. Total Variation Minimization and a Class of Binary MRF Models , 2005, EMMCVPR.

[3] Truong Q. Nguyen,et al. Compression artifact reduction based on total variation regularization method for MPEG-2 , 2011, IEEE Transactions on Consumer Electronics.

[4] L. Rudin,et al. Nonlinear total variation based noise removal algorithms , 1992 .

[5] Erik Lindholm,et al. NVIDIA Tesla: A Unified Graphics and Computing Architecture , 2008, IEEE Micro.

[6] Tomio Goto,et al. Super-resolution System for 4K-HDTV , 2014, 2014 22nd International Conference on Pattern Recognition.