多任务学习框架下的单帧图像超分辨率重建-仲恺农业工程学院.PDFVIP

28 4 Vol． 28 ，No． 4 第 卷 第 期 仲恺农业工程学院学报 2015 12 Journal of Zhongkai University of Agriculture and Engineering December ，2015 年 月 DOI : 10． 3969 /j． issn． 1674 － 5663． 2015． 04． 011 Single image super-resolution using multi-task learning framework WU Yarong (Department of Science and Technology ，Zhongkai University of Agriculture and Engineering ，Guangzhou 510225 ，China) Abstract :For making full use of the property of self similarity ，a novel SISＲ method based on a variant of Gaussian process regression (GPＲ)was proposed by considering it as a multi-task learning problem． This method could efficiently suppress the artifacts along the salient edges and produce natural looking ap- pearance in the final high resolution (HＲ)results． Extensive experimental results demonstrated that the results produced by our method could be equivalent or superior to other state of the art algorithms． Key words :single image super-resolution ;multi-task learning ;gaussian process regression ;self-similarity CLC number :TP751. 1 Document code :A Article ID :1674 － 5663 (2015)04 － 0050 － 04 多任务学习框架下的单帧图像超分辨率重建 吴亚榕 ( ， 510225) 仲恺农业工程学院科技处 广东广州 : ， ， 摘要 为了充分利用图像的自相似性质 针对图像的超分辨率重建问题构造了一个多任务学习的问题 并基于高 ， ． 斯过程回归进一步扩展 提出了一个新颖的单帧图像超分辨率重建算法 该算法能够