Improved 3D Point-Line Mapping Regression for Camera Relocalization
This work addresses camera relocalization for robotics or AR/VR applications, but it is incremental as it builds on existing methods by modifying the feature learning approach.
The paper tackles the problem of camera relocalization by improving 3D point and line mapping regression, proposing an architecture that learns point and line features independently to avoid overfitting and reduce computational costs, resulting in significant performance enhancements as demonstrated experimentally.
In this paper, we present a new approach for improving 3D point and line mapping regression for camera re-localization. Previous methods typically rely on feature matching (FM) with stored descriptors or use a single network to encode both points and lines. While FM-based methods perform well in large-scale environments, they become computationally expensive with a growing number of mapping points and lines. Conversely, approaches that learn to encode mapping features within a single network reduce memory footprint but are prone to overfitting, as they may capture unnecessary correlations between points and lines. We propose that these features should be learned independently, each with a distinct focus, to achieve optimal accuracy. To this end, we introduce a new architecture that learns to prioritize each feature independently before combining them for localization. Experimental results demonstrate that our approach significantly enhances the 3D map point and line regression performance for camera re-localization. The implementation of our method will be publicly available at: https://github.com/ais-lab/pl2map/.