A method of decomposing a set of scans of different views of overlapping objects into constituent objects is presented. The method involves an initialization process whereby keypoints in two views are determined and matched, disparity between keypoint pairs are computed, and the keypoints are grouped into clusters based on their disparities. Following the initialization process is an iterative optimization process whereby a cost function is calculated and minimized assuming a fixed composition matrix and re-solved assuming a fixed attenuation coefficient. Then, the composition matrix and the attenuation coefficient are updated simultaneously, and the solving, the re-solving, and the updating steps are repeated until there is no significant improvement in the result.