Paying Attention to Activation Maps in Camera Pose Regression

03/21/2021
by   Yoli Shavit, et al.
0

Camera pose regression methods apply a single forward pass to the query image to estimate the camera pose. As such, they offer a fast and light-weight alternative to traditional localization schemes based on image retrieval. Pose regression approaches simultaneously learn two regression tasks, aiming to jointly estimate the camera position and orientation using a single embedding vector computed by a convolutional backbone. We propose an attention-based approach for pose regression, where the convolutional activation maps are used as sequential inputs. Transformers are applied to encode the sequential activation maps as latent vectors, used for camera pose regression. This allows us to pay attention to spatially-varying deep features. Using two Transformer heads, we separately focus on the features for camera position and orientation, based on how informative they are per task. Our proposed approach is shown to compare favorably to contemporary pose regressors schemes and achieves state-of-the-art accuracy across multiple outdoor and indoor benchmarks. In particular, to the best of our knowledge, our approach is the only method to attain sub-meter average accuracy across outdoor scenes. We make our code publicly available from here.

READ FULL TEXT

page 1

page 6

page 7

research
03/21/2021

Learning Multi-Scene Absolute Pose Regression with Transformers

Absolute camera pose regressors estimate the position and orientation of...
research
03/05/2023

HyperPose: Camera Pose Localization using Attention Hypernetworks

In this study, we propose the use of attention hypernetworks in camera p...
research
09/08/2019

AtLoc: Attention Guided Camera Localization

Deep learning has achieved impressive results in camera localization, bu...
research
07/12/2022

Camera Pose Auto-Encoders for Improving Pose Regression

Absolute pose regressor (APR) networks are trained to estimate the pose ...
research
03/05/2023

Learning to Localize in Unseen Scenes with Relative Pose Regressors

Relative pose regressors (RPRs) localize a camera by estimating its rela...
research
12/22/2020

Do We Really Need Scene-specific Pose Encoders?

Visual pose regression models estimate the camera pose from a query imag...
research
03/05/2023

Estimating Extreme 3D Image Rotation with Transformer Cross-Attention

The estimation of large and extreme image rotation plays a key role in m...

Please sign up or login with your details

Forgot password? Click here to reset