Reassessing the Limitations of CNN Methods for Camera Pose Regression
This addresses camera pose estimation for outdoor and indoor scenarios, representing a strong specific gain in a domain-specific area.
The paper tackles camera pose estimation by proposing a regression model that directly predicts poses from images, achieving significantly higher accuracy than existing regression methods through a novel training technique that generates synthetic training views guided by probability distributions from the training set to overcome biased data.
In this paper, we address the problem of camera pose estimation in outdoor and indoor scenarios. In comparison to the currently top-performing methods that rely on 2D to 3D matching, we propose a model that can directly regress the camera pose from images with significantly higher accuracy than existing methods of the same class. We first analyse why regression methods are still behind the state-of-the-art, and we bridge the performance gap with our new approach. Specifically, we propose a way to overcome the biased training data by a novel training technique, which generates poses guided by a probability distribution from the training set for synthesising new training views. Lastly, we evaluate our approach on two widely used benchmarks and show that it achieves significantly improved performance compared to prior regression-based methods, retrieval techniques as well as 3D pipelines with local feature matching.