This article presents a new spectral reflectance reconstruction method based on Wiener estimation which adaptively reorganizes the training set according to the multi-channel image. First, the initial approximation of the spectral reflectance is reconstructed from the multi-channel images using Wiener estimation. The spectral similarities between each spectral reflectance in the original training set and the initial approximation of the spectral reflectance are then calculated using a correlation coefficient. Next, the similar training set is adaptively organized from the original training set in accordance with each spectral similarity. The final approximation of the spectral reflectance is reconstructed applying the similar training set to Wiener estimation. The performance of the proposed method is objectively compared with previous methods based on the root mean square error and shown to improve the accuracy of the spectral reflectance reconstruction.