End-to-end learning of keypoint detection and matching for relative pose estimation
This work addresses visual localization for applications like robotic mapping, navigation, and AR, but it is incremental as it follows a traditional pipeline with end-to-end learning.
The paper tackles the problem of relative pose estimation between images by jointly learning keypoint detection, description extraction, matching, and pose estimation in an end-to-end manner, achieving state-of-the-art localization accuracy on the 7 Scenes dataset.
We propose a new method for estimating the relative pose between two images, where we jointly learn keypoint detection, description extraction, matching and robust pose estimation. While our architecture follows the traditional pipeline for pose estimation from geometric computer vision, all steps are learnt in an end-to-end fashion, including feature matching. We demonstrate our method for the task of visual localization of a query image within a database of images with known pose. Pairwise pose estimation has many practical applications for robotic mapping, navigation, and AR. For example, the display of persistent AR objects in the scene relies on a precise camera localization to make the digital models appear anchored to the physical environment. We train our pipeline end-to-end specifically for the problem of visual localization. We evaluate our proposed approach on localization accuracy, robustness and runtime speed. Our method achieves state of the art localization accuracy on the 7 Scenes dataset.