Abstract

Join us on Zoom

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

BIO:

Dr Yoli Shavit is a Principal Research Scientist Manager at Huawei Tel Aviv Research Center (TRC) and a Postdoctoral Researcher at Bar-Ilan University. Before joining Huawei, Yoli worked at Amazon and interned at Microsoft Research. She holds a PhD in Computer Science from the University of Cambridge, an MSc in Bioinformatics from Imperial College London and a BSc in Computer Science and in Life Science from Tel Aviv University. Yoli is the recipient of the Cambridge International Scholarship, and her thesis was nominated for the best thesis award in the UK. Her current research focuses on deep learning methods for camera localization and multi-view stereo, with recent publications in CVPR , ICCV, ECCV and NeurIPS.