![]() ![]() Our experiments demonstrate that the proposed algorithm compares favorably in terms of reconstruction accuracy and the ability to expose reconstruction uncertainty.” We compare our method to two state-of-the-art volumetric reconstruction algorithms on three challenging aerial datasets with LIDAR ground truth. Moreover, the proposed algorithm allows for a Bayes optimal prediction with respect to a natural reconstruction loss. In contrast to the MAP solution, marginals encode the underlying uncertainty and ambiguity in the reconstruction. Our main contribution is an approximate highly parallelized discrete-continuous inference algorithm to compute the marginal distributions of each voxel’s occupancy and appearance. ![]() We formulate the problem as inference in a Markov random field, which accurately captures the dependencies between the occupancy and appearance of each voxel, given all input images. “This paper presents a novel probabilistic foundation for volumetric 3-d reconstruction. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |