Multiview Image-Based Localization
This work addresses camera localization for applications like augmented reality or robotics, offering an incremental improvement over existing image retrieval and 3D reconstruction methods.
The paper tackles the problem of poor localization accuracy in image retrieval-based camera pose estimation by introducing a hybrid method that decouples translation and rotation estimation and uses multiview correspondences directly. The approach achieves improved performance on the 7-Scenes and Cambridge Landmarks datasets, with better timing and memory footprint compared to state-of-the-art methods.
The image retrieval (IR) approach to image localization has distinct advantages to the 3D and the deep learning (DNN) approaches: it is seen-agnostic, simpler to implement and use, has no privacy issues, and is computationally efficient. The main drawback of this approach is relatively poor localization in both position and orientation of the query camera when compared to the competing approaches. This paper represents a hybrid approach that stores only image features in the database like some IR methods, but relies on a latent 3D reconstruction, like 3D methods but without retaining a 3D scene reconstruction. The approach is based on two ideas: {\em (i)} a novel proposal where query camera center estimation relies only on relative translation estimates but not relative rotation estimates through a decoupling of the two, and {\em (ii)} a shift from computing optimal pose from estimated relative pose to computing optimal pose from multiview correspondences, thus cutting out the ``middle-man''. Our approach shows improved performance on the 7-Scenes and Cambridge Landmarks datasets while also improving on timing and memory footprint as compared to state-of-the-art.