Learning to Localize in Unseen Scenes with Relative Pose Regressors
This work addresses the generalization issue in camera localization for robotics and AR/VR applications, representing an incremental improvement over existing RPR methods.
The paper tackled the problem of relative pose regressors (RPRs) performing poorly in unseen scenes by proposing a method that aggregates paired feature maps into latent codes and uses a continuous rotation representation, resulting in significantly better localization in unseen environments across indoor and outdoor benchmarks while maintaining competitive performance in seen scenes.
Relative pose regressors (RPRs) localize a camera by estimating its relative translation and rotation to a pose-labelled reference. Unlike scene coordinate regression and absolute pose regression methods, which learn absolute scene parameters, RPRs can (theoretically) localize in unseen environments, since they only learn the residual pose between camera pairs. In practice, however, the performance of RPRs is significantly degraded in unseen scenes. In this work, we propose to aggregate paired feature maps into latent codes, instead of operating on global image descriptors, in order to improve the generalization of RPRs. We implement aggregation with concatenation, projection, and attention operations (Transformer Encoders) and learn to regress the relative pose parameters from the resulting latent codes. We further make use of a recently proposed continuous representation of rotation matrices, which alleviates the limitations of the commonly used quaternions. Compared to state-of-the-art RPRs, our model is shown to localize significantly better in unseen environments, across both indoor and outdoor benchmarks, while maintaining competitive performance in seen scenes. We validate our findings and architecture design through multiple ablations. Our code and pretrained models is publicly available.