HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset

In this work, we propose HyperPose, which utilizes hypernetworks in absolute camera pose regressors. The inherent appearance variations in natural scenes, attributable to environmental conditions, perspective, and lighting, induce a significant domain disparity between the training and test datasets. This disparity degrades the precision of contemporary localization networks. To mitigate this, we advocate for incorporating hypernetworks into single-scene and multiscene camera pose regression models. During inference, the hypernetwork dynamically computes adaptive weights for the localization regression heads based on the particular input image, effectively narrowing the domain gap. Using indoor and outdoor datasets, we evaluate the HyperPose methodology across multiple established absolute pose regression architectures. We also introduce and share the Extended Cambridge Landmarks (ECL), a novel localization dataset, based on the Cambridge Landmarks dataset, showing it in multiple seasons with significantly varying appearance conditions. Our empirical experiments demonstrate that HyperPose yields notable performance enhancements for single- and multi-scene architectures.

The Extended Cambridge Landmarks (ECL) dataset introduces new flavors for the scenes in the original Cambridge Landmarks dataset. For each scene, the ECL contains three distinct flavors: Evening, Winter, and Summer.
The ECL dataset can be downloaded from this link: Extended Cambridge Landmarks (ECL) Dataset Repo