Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement

TL;DR

This paper introduces a self-supervised method that jointly learns neural implicit scene representations and dense features, improving camera pose refinement by aligning volumetric and image features through contrastive learning.

Contribution

It proposes a novel joint learning framework for implicit scene representation and feature extraction, enhancing visual localization accuracy and robustness.

Findings

Outperforms prior methods on real-world scenes

Produces discriminative, viewpoint-invariant features

Effectively leverages implicit 3D geometry for localization

Abstract

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former requires sparse feature extractors and matchers to build the scene representation. The latter might lack geometric grounding not capturing the 3D structure of the scene well enough. This paper proposes to jointly learn the scene representation along with a 3D dense feature field and a 2D feature extractor whose outputs are embedded in the same metric space. Through a contrastive framework we align this volumetric field with the image-based extractor and regularize the latter with a ranking loss from learned surface information. We learn the underlying geometry of the scene with an implicit field through volumetric rendering and design our feature field to leverage intermediate geometric information encoded in the implicit field. The resulting features are discriminative and robust to viewpoint change while maintaining rich encoded information. Visual localization is then achieved by aligning the image-based features and the rendered volumetric features. We show the effectiveness of our approach on real-world scenes, demonstrating that our approach outperforms prior and concurrent work on leveraging implicit scene representations for localization.