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/

翻译：相机姿态估计是一个长期存在的计算机视觉问题，至今仍常依赖经典方法，如手工特征匹配、RANSAC和光束法平差。本文提出将运动恢复结构（SfM）问题纳入概率扩散框架，对给定输入图像条件下相机姿态的条件分布进行建模。这一对旧问题的新视角具有多重优势：(i) 扩散框架的本质与光束法平差的迭代过程相呼应；(ii) 该公式允许无缝集成对极几何的几何约束；(iii) 在具有宽基线的稀疏视图等典型困难场景中表现出色；(iv) 该方法可预测任意数量图像的内部和外部参数。我们证明，所提出的PoseDiffusion方法在两个真实世界数据集上显著优于经典SfM流程和学习方法。最后，观察到我们的方法无需额外训练即可跨数据集泛化。项目页面：https://posediffusion.github.io/