Learning Multi-Scene Absolute Pose Regression with Transformers

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 with images and pose labels to embed a single reference scene at a time. Recently, this scheme was extend...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Shavit, Yoli, Ferens, Ron, Keller, Yosi
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.07.2021
Subjects
Cameras
Coders
Decoders
Learning
Multilayers
Transformers
Online AccessGet full text

Cover

More Information
Summary: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 with 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.
ISSN:2331-8422