The invention discloses a graph-model-based single image super-resolution output method. The graph-model-based single image super-resolution output method includes the following steps: 1) according toa preset sampling rate, performing interpolation on an input single image by means of a bicubic interpolation method, obtaining a low resolution image, segmenting the obtained low resolution image into m*n image blocks, calculating the Euclidean distance of the pixel value of each image block, and according to the Euclidean distance, determining a set of similar blocks, wherein each image block in the segmented low resolution image has one set of similar blocks; 2) constructing a graph model for the set of similar blocks; 3) performing Laplace transformation on the obtained two dimensional matrix to obtain a Laplace matrix, and then carrying out restoration of the image blocks through solution by means of an optimization formula; and 4) averaging and reconstructing the restored image block set, and finally obtaining a super-resolution image. The graph-model-based single image super-resolution output method can overcome the defect that a machine learning method needs mass image data totrain a model, thus being more suitable for image super resolution.