Roxels: Responsibility Weighted 3D Volume Reconstruction

This paper examines the problem of reconstructing a voxelized representation of 3D space from a series of images. An iterative algorithm is used to find the scene model which jointly explains all the observed images by determining which region of space is responsible for each of the observations. The current approach formulates the problem as one of optimization over estimates of these responsibilities. The process converges to a distribution of responsibility which accurately reflects the constraints provided by the observations, the positions and shape of both solid and transparent objects, and the uncertainty which remains. Reconstruction is robust, and gracefully represents regions of space in which there is little certainty about the exact structure due to limited, non-existent, or contradicting data. Rendered images of voxel spaces recovered from synthetic and real observation images are shown. To Appear: International Conference on Computer Vision, 1999

• Type: Conference
• Year: 1999
• Where: ICCV
• Authors: Jeremy S. De Bonet, Paul A. Viola
• Keywords: Computer Vision, ICCV 1999, Iterative Algorithm, Little Certainty, Observed Images, Real Observation Images, Voxel Spaces