ImLoc: Revisiting Visual Localization with Image-based Representation
This work addresses the problem of balancing accuracy and practicality in visual localization for applications like robotics and augmented reality, offering an incremental improvement over existing methods.
The paper tackles the trade-off between ease of maintenance and geometric accuracy in visual localization by proposing a 2D image-based representation augmented with depth maps, achieving state-of-the-art accuracy on standard benchmarks and outperforming memory-efficient methods at comparable map sizes.
Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based, which achieve high accuracy but require a centralized reconstruction and are difficult to update. In this work, we revisit visual localization with a 2D image-based representation and propose to augment each image with estimated depth maps to capture the geometric structure. Supported by the effective use of dense matchers, this representation is not only easy to build and maintain, but achieves highest accuracy in challenging conditions. With compact compression and a GPU-accelerated LO-RANSAC implementation, the whole pipeline is efficient in both storage and computation and allows for a flexible trade-off between accuracy and highest memory efficiency. Our method achieves a new state-of-the-art accuracy on various standard benchmarks and outperforms existing memory-efficient methods at comparable map sizes. Code will be available at https://github.com/cvg/Hierarchical-Localization.