Insights on Evaluation of Camera Re-localization Using Relative Pose Regression

09/23/2020
by   Amir Shalev, et al.
0

We consider the problem of relative pose regression in visual relocalization. Recently, several promising approaches have emerged in this area. We claim that even though they demonstrate on the same datasets using the same split to train and test, a faithful comparison between them was not available since on currently used evaluation metric, some approaches might perform favorably, while in reality performing worse. We reveal a tradeoff between accuracy and the 3D volume of the regressed subspace. We believe that unlike other relocalization approaches, in the case of relative pose regression, the regressed subspace 3D volume is less dependent on the scene and more affect by the method used to score the overlap, which determined how closely sampled viewpoints are. We propose three new metrics to remedy the issue mentioned above. The proposed metrics incorporate statistics about the regression subspace volume. We also propose a new pose regression network that serves as a new baseline for this task. We compare the performance of our trained model on Microsoft 7-Scenes and Cambridge Landmarks datasets both with the standard metrics and the newly proposed metrics and adjust the overlap score to reveal the tradeoff between the subspace and performance. The results show that the proposed metrics are more robust to different overlap threshold than the conventional approaches. Finally, we show that our network generalizes well, specifically, training on a single scene leads to little loss of performance on the other scenes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/25/2022

RELMOBNET: A Robust Two-Stage End-To-End Training Approach For MOBILENETV3 Based Relative Camera Pose Estimation

Relative camera pose estimation plays a pivotal role in dealing with 3D ...
research
10/11/2022

Map-free Visual Relocalization: Metric Pose Relative to a Single Image

Can we relocalize in a scene represented by a single reference image? St...
research
08/04/2019

To Learn or Not to Learn: Visual Localization from Essential Matrices

Visual localization is the problem of estimating a camera within a scene...
research
12/31/2018

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion

Estimating the relative rigid pose between two RGB-D scans of the same u...
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
03/23/2017

Robust SfM with Little Image Overlap

Usual Structure-from-Motion (SfM) techniques require at least trifocal o...
research
09/10/2020

A First Step Towards Distribution Invariant Regression Metrics

Regression evaluation has been performed for decades. Some metrics have ...

Please sign up or login with your details

Forgot password? Click here to reset