@inproceedings{5035bcd989db43749f1adff417239817,
title = "Learning Multi-Scene Absolute Pose Regression with Transformers",
abstract = "Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained using images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended for learning multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent features and scenes encoding into candidate pose predictions. This mechanism allows our model to focus on general features that are informative for localization while embedding multiple scenes in parallel. We evaluate our method on commonly benchmarked indoor and outdoor datasets and show that it surpasses both multi-scene and state-of-the-art single-scene absolute pose regressors. We make our code publicly available from https://github.com/yolish/multi-scene-pose-transformer.",
author = "Yoli Shavit and Ron Ferens and Yosi Keller",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 ; Conference date: 11-10-2021 Through 17-10-2021",
year = "2021",
doi = "https://doi.org/10.1109/ICCV48922.2021.00273",
language = "الإنجليزيّة",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2713--2722",
booktitle = "Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021",
address = "الولايات المتّحدة",
}