Joint sub-band based neighbor embedding for image super-resolution | |
Song, Sijie ; Li, Yanghao ; Liu, Jiaying ; Quo, Zongming | |
2016 | |
英文摘要 | In this paper, we propose a novel neighbor embedding method based on joint sub-bands for image super-resolution. Rather than directly reconstructing the total spatial variations of the input image, we restore each frequency component separately. The input LR image is decomposed into sub-bands defined by steerable filters to capture structural details on different directional frequency components. Then the neighbor embedding principle is employed to reconstruct each band, respectively. Moreover, taken the diverse characteristics of each band into account, we adopt adaptive similarity criteri-ons for searching nearest neighbors. Finally, we recombine the generated HR sub-bands by applying the inverting subband decomposition to get the final super-resolved result. Experimental results demonstrate the effectiveness of our method both in objective and subjective qualities comparing with other state-of-the-art methods. ? 2016 IEEE.; EI; 1661-1665; 2016-May |
语种 | 中文 |
出处 | 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 |
DOI标识 | 10.1109/ICASSP.2016.7471959 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/436172] |
专题 | 计算机科学技术研究所 |
推荐引用方式 GB/T 7714 | Song, Sijie,Li, Yanghao,Liu, Jiaying,et al. Joint sub-band based neighbor embedding for image super-resolution. 2016-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论