HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

TL;DR

HSCNet++ introduces a hierarchical scene coordinate classification and regression approach using transformers, enabling robust and scalable single-image visual localization in large and complex environments.

Contribution

It extends HSCNet with a hierarchical structure and transformer components, improving localization accuracy and scalability in large scenes.

Findings

Sets new state-of-the-art on multiple indoor datasets.

Models are compact and scalable to large environments.

Achieves robust pixel scene coordinate prediction.

Abstract

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress the mapping between raw pixels and 3D coordinates in the scene, and thus the matching is implicitly performed by the forward pass through the network. However, in a large and ambiguous environment, learning such a regression task directly can be difficult for a single network. In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image. The proposed method, which is an extension of HSCNet, allows us to train compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image localization on the 7-Scenes, 12 Scenes, Cambridge Landmarks datasets, and the combined indoor scenes.