PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment
This addresses the computer vision problem of camera pose estimation, offering a novel approach that enhances performance in challenging scenarios like sparse views with wide baselines.
The paper tackles camera pose estimation by formulating Structure from Motion within a probabilistic diffusion framework, modeling the conditional distribution of camera poses from images, and demonstrates significant improvements over classic and learned methods on real-world datasets with generalization across datasets.
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/