摘要
针对单帧图像超分辨率重建提出一种基于反向投影的单帧图像超分辨率重建方法。根据迭代反向投影算法的思想,使用估计高分辨率图像得到4幅模拟低分辨率图像,并将其与实际低分辨率图像的误差图像进行反向投影。在反向投影过程中,自适应地对其权重进行计算,用来更新原先的估计高分辨率图像。实验结果表明,该方法对于不同的降质模型有较好的鲁棒性,计算量小,能有效提高单帧图像超分辨率重建的质量。
Proposes a single-frame image super-resolution reconstruction method based on back-projection.According to the thought of iterative back-projection algorithms,uses the high-resolution image to get 4 simulate low-resolution images,uses the error image between simulated low-resolution images and the actual low-resolution images to do back-projection.In the projection process,the weights of error images are adaptive,uses these error images to update the high-resolution image.The experimental results show that the proposed algorithm for different degradation models has good robustness,and small amount of calculation.The method can improve the quality of single frame image super-resolution reconstruction.
基金
国家自然科学基金面上项目(No.61071162)
关键词
超分辨率重建
迭代反向投影
自适应
鲁棒性
Super-Resolution Resconstruction
Iterative Back-Projection
Adaptive
Robustness