METHODOLOGY FOR THREE-DIMENSIONAL SCENE RECONSTRUCTION FROM TWO-DIMENSIONAL IMAGE SEQUENCES

摘要

The present invention relates to a system and method for interactive and iterative reconstruction, helping to reduce computational requirements by generating a model from a subset of the available data, and then refining the model using additional data. Example embodiments of the present invention reconstruct a three-dimensional scene from a plurality of two-dimensional images of that scene by generating a model of the three-dimensional scenes from a subset of the two-dimensional images. The model can then be refined using specific characteristics for each image in the subset, which are calculated using the other images in the subset. The model is further refined by using images that were not in the original subset.;COPYRIGHT KIPO 2015