Continual Learning for Image-Based Camera Localization

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks has shown great potential. However, such methods assume a stationary data distribution with all scenes simultaneously available during training. In this paper, we approach the problem of visual localization in a continual learning setup -- whereby the model is trained on scenes in an incremental manner. Our results show that similar to the classification domain, non-stationary data induces catastrophic forgetting in deep networks for visual localization. To address this issue, a strong baseline based on storing and replaying images from a fixed buffer is proposed. Furthermore, we propose a new sampling method based on coverage score (Buff-CS) that adapts the existing sampling strategies in the buffering process to the problem of visual localization. Results demonstrate consistent improvements over standard buffering methods on two challenging datasets -- 7Scenes, 12Scenes, and also 19Scenes by combining the former scenes.

DOI

10.1109/ICCV48922.2021.00324

Citation

Wang, S, Laskar, Z, Melekhov, I, Li, X & Kannala, J 2022, Continual Learning for Image-Based Camera Localization . in 2021 International Conference on Computer Vision, ICCV . IEEE International Conference on Computer Vision, IEEE, pp. 3232-3242, International Conference on Computer Vision, Virtual, Online, 11/10/2021 . https://doi.org/10.1109/ICCV48922.2021.00324

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202203032068

Collections

[article-cris] Perustieteiden korkeakoulu / SCI

Show all metadata