| Image editing is an important branch in the field of image processing.The time complexity and the space complexity of the editing algorithm are closely related to the image resolution.With the continuous development of imaging equipment and imaging technology,the information stored in the image becomes larger and larger,and the resolution of the image is higher and higher,which poses a serious challenge to image editing technology.Computational and memory costs often require that a smaller solution be run over a downsampled image.Although general purpose upsampling methods can be used to interpolate the low resolution solution to the full resolution,the upsampled images typically suffer from blurring of sharp edges,because of the smoothness prior inherent in the linear interpolation filters.We propose to leverage the fact that we have a high-resolution image in addition to the low-resolution solution.The algorithm considers the local properties of the image in the color space,and use the high-resolution image as a guided image.Our approach can produce very good full resolution results from solutions computed at very low resolutions.We show results for image smoothing,image colorization,adaptive tone mapping,etc. |
