Spectral Partitioning for Structure from MotionReportar como inadecuado

Spectral Partitioning for Structure from Motion

Spectral Partitioning for Structure from Motion - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

We propose a spectral partitioning approach for large-scaleoptimization problems, specifically structure from motion.In structure from motion, partitioning methods reduce theproblem into smaller and better conditioned subproblemswhich can be efficiently optimized. Our partitioning methoduses only the Hessian of the reprojection error and its eigenvectors.We show that partitioned systems that preserve theeigenvectors corresponding to small eigenvalues result inlower residual error when optimized. We create partitionsby clustering the entries of the eigenvectors of the Hessiancorresponding to small eigenvalues. This is a more generaltechnique than relying on domain knowledge and heuristicssuch as bottom-up structure from motion approaches. Simultaneously,it takes advantage of more information thangeneric matrix partitioning algorithms.

Computational Perception and Robotics - Computational Perception and Robotics Publications -

Autor: Steedly, Drew - Essa, Irfan - Dellaert, Frank - -

Fuente: https://smartech.gatech.edu/

Documentos relacionados