[CVPR 2023] Power Bundle Adjustment for Large-Scale 3D Reconstruction скачать в хорошем качестве

[CVPR 2023] Power Bundle Adjustment for Large-Scale 3D Reconstruction

Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Publication: Power Bundle Adjustment for Large-Scale 3D Reconstruction Authors: Simon Weber, Nikolaus Demmel, Tin Chon Chan, Daniel Cremers Paper: https://arxiv.org/abs/2204.12834 GitHub: https://github.com/simonwebertum/poba Abstract: We introduce Power Bundle Adjustment as an expansion type algorithm for solving large-scale bundle adjustment problems. It is based on the power series expansion of the inverse Schur complement and constitutes a new family of solvers that we call inverse expansion methods. We theoretically justify the use of power series and we prove the convergence of our approach. Using the real-world BAL dataset we show that the proposed solver challenges the state-of-the-art iterative methods and significantly acceleates the solution of the normal equation, even for reaching a very high accuracy. This easy-to-implement solver can also complement a recently presented distributed bundle adjustment framework. We demonstrate that employing the proposed Power Bundle Adjustment as a sub-problem solver significantly improves speed and accuracy of the distributed optimization.