Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Understand

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms.

• Many regress precise geometric quantities, like poses or 3D points, from an input image.
• This either fails to generalize to new viewpoints or ties the model parameters to a specific scene.
• In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms.