Learning Neural Volumetric Pose Features for Camera Localization
This work addresses camera localization for computer vision applications, representing a strong specific gain in accuracy.
The paper tackles camera localization by introducing PoseMap, a neural volumetric pose feature, and achieves a 14.28% average performance gain in indoor scenes and 20.51% in outdoor scenes compared to existing methods.
We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose Regression (APR) architecture, together with an augmented NeRF module. This integration not only facilitates the generation of novel views to enrich the training dataset but also enables the learning of effective pose features. Additionally, we extend our architecture for self-supervised online alignment, allowing our method to be used and fine-tuned for unlabelled images within a unified framework. Experiments demonstrate that our method achieves 14.28% and 20.51% performance gain on average in indoor and outdoor benchmark scenes, outperforming existing APR methods with state-of-the-art accuracy.