In order to solve the problem that classical Laplacian Pyramid (LP) transformin image fusion losses high frequency information of the fused image seriously and has no translation invariance, with the use of non-separable wavelet which has translation invariance and accurate description of image details, a new construction method of non-sampling non-separable LP was proposed and applied to the multi-spectral image fusion. Firstly, a six-channel non-separable low-pass filter was constructed and used to construct non-sampling non-separable wavelet pyramid for multi-spectral image and panchromatic image, and then the image was processed by non-sampling non-separable LP decomposition. Then, different fusion rules were used for the fusion of different decomposition layers. Finally, the fused image was obtained by using non-separable LP reconstruction algorithm. The experimental results show that compared with the algorithms based on Discrete Wavelet Transformation (DWT), Contourlet Transformation (CT), and Midway Histogram Equalization (MHE), the spatial correlation coefficient of the proposed method was increased by 1.84%, 1.56%, and 11.06% respectively, and the relative global dimensional synthesis error of the proposed method was reduced by 49.26%, 48.15%, and 89.19% respectively. The proposed method can effectively improve the spatial resolution while obtaining good spectral information of image, well preserve the edge information and structure information of the image.