[ECCV 2024] Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment
Автор: cvprtum
Загружено: 2024-09-12
Просмотров: 434
European Conference on Computer Vision (ECCV), 2024
Authors: Simon Weber, Je Hyeong Hong, Daniel Cremers
Paper: https://arxiv.org/abs/2405.05079
Github: https://arxiv.org/abs/2405.05079
Abstract:
Most Bundle Adjustment (BA) solvers like the Levenberg-Marquardt algorithm require a good initialization. Instead, initialization-free BA remains a largely uncharted territory. The under-explored Variable Projection algorithm (VarPro) exhibits a wide convergence basin even without initialization. Coupled with object space error formulation, recent works have shown its ability to solve small-scale initialization-free bundle adjustment problem. To make such initialization-free BA approaches scalable, we introduce Power Variable Projection (PoVar), extending a recent inverse expansion method based on power series. Importantly, we link the power series expansion to Riemannian manifold optimization. This projective framework is crucial to solve large-scale bundle adjustment problems without initialization. Using the real-world BAL dataset, we experimentally demonstrate that our solver achieves state-of-the-art results in terms of speed and accuracy. To our knowledge, this work is the first to address the scalability of BA without initialization opening new venues for initialization-free structure-from-motion.
![[ECCV 2024] Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment](https://ricktube.ru/thumbnail/PlFrfTaMfPc/hq720.jpg)
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
![[ICLR25] Implicit Neural Surface Deformation with Explicit Velocity Fields](https://ricktube.ru/thumbnail/XHmO9ZSLhXM/mqdefault.jpg)
![[CVPR 2025] Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction](https://ricktube.ru/thumbnail/Hrnd-xrkvEA/mqdefault.jpg)
