METHOD AND DEVICE FOR OPTIMIZING THREE-DIMENSIONAL RECONSTRUCTION MODEL, AND MOVABLE PLATFORM

摘要

A method and device for optimizing a three-dimensional reconstruction model, and a movable platform, the method comprising: acquiring reprojection errors of each facet in a three-dimensional reconstruction model to be optimized of a target object separately projected into M reference images (S201); according to the reprojection errors of the facets separately projected into the M reference images, determining whether the facets are facets to be optimized (S202); and if the facets are facets to be optimized, then adjusting the positions of the facets in the three-dimensional reconstruction model so as to obtain an optimized three-dimensional reconstruction model (S203). The three-dimensional reconstruction model is a model that is generated according to N initial images comprising at least a partial image of the target object and that is composed of multiple facets, and the reference images are images obtained by down-sampling the initial images by L levels. The optimization efficiency of the three-dimensional reconstruction model is improved, and the probability of noise introduction is reduced.