PoseDiffusion：通过扩散辅助捆绑调整解决姿势估计

摘要

相机姿态估计是一个长期存在的计算机视觉问题，迄今通常依赖于传统方法，如手工制作的关键点匹配、RANSAC 和捆绑调整。在本文中，我们提出在概率扩散框架内制定运动结构（SfM）问题，建模给定输入图像时相机姿态的条件分布。这种对一个古老问题的新颖观点具有几个优点。 (i) 扩散框架的性质反映了捆绑调整的迭代过程。 (ii) 该公式允许无缝集成来自极线几何的几何约束。 (iii) 它在典型的困难场景中表现出色，如稀疏视图和宽基线。 (iv) 该方法可以预测任意数量图像的内参和外参。我们证明了我们的 PoseDiffusion 方法在两个真实世界数据集上明显优于经典 SfM 流水线和学习方法。最后，观察到我们的方法可以在不经过进一步训练的情况下在数据集之间进行泛化。项目页面：https://posediffusion.github.io/

English

Camera pose estimation is a long-standing computer vision problem that to date often relies on classical methods, such as handcrafted keypoint matching, RANSAC and bundle adjustment. In this paper, we propose to formulate the Structure from Motion (SfM) problem inside a probabilistic diffusion framework, modelling the conditional distribution of camera poses given input images. This novel view of an old problem has several advantages. (i) The nature of the diffusion framework mirrors the iterative procedure of bundle adjustment. (ii) The formulation allows a seamless integration of geometric constraints from epipolar geometry. (iii) It excels in typically difficult scenarios such as sparse views with wide baselines. (iv) The method can predict intrinsics and extrinsics for an arbitrary amount of images. We demonstrate that our method PoseDiffusion significantly improves over the classic SfM pipelines and the learned approaches on two real-world datasets. Finally, it is observed that our method can generalize across datasets without further training. Project page: https://posediffusion.github.io/

PoseDiffusion：通过扩散辅助捆绑调整解决姿势估计

PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

摘要

Support