The objective of this study is to compare landmark-based assessment of hominin mandible morphological variation with that from a high-density point cloud, using 3D models constructed from structure-from-motion (SfM) surface capture techniques. Surface models of nine hominin mandible casts were created using SfM photogrammetry. The morphology of these models was described using traditional geometric morphometrics based on identification of landmarks. This was compared to the morphological variation described by the differences between high-density point clouds, which do not rely on anatomical landmarks, using an iterative closest point algorithm. The landmark-based approach grouped the anatomically modern human and Neanderthal mandibles with reasonable success. The high-density point cloud approach also grouped these successfully, but was able to incorporate information from a specimen that was insufficiently preserved to be included in the landmark data set. This improved the accuracy of the grouping. The use of high-density point clouds from surface capture to analyse hominin mandible morphology allows for greater amounts of information to be included and offers a potential method to identify shape affinity that is as successful as landmark-based geometric morphometrics.