FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation

Estimating relative camera poses between images has been a central problem in computer vision. Methods that find correspondences and solve for the fundamental matrix offer high precision in most cases. Conversely, methods predicting pose directly using neural networks are more robust to limited over...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Rockwell, Chris, Kulkarni, Nilesh, Jin, Linyi, Park, Jeong Joon, Johnson, Justin, Fouhey, David F
Format: Article
Language:English
Subjects:
Cameras
Computer vision
Estimation
Feature extraction
Neural networks
Pose estimation
Robustness
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Estimating relative camera poses between images has been a central problem in computer vision. Methods that find correspondences and solve for the fundamental matrix offer high precision in most cases. Conversely, methods predicting pose directly using neural networks are more robust to limited overlap and can infer absolute translation scale, but at the expense of reduced precision. We show how to combine the best of both methods; our approach yields results that are both precise and robust, while also accurately inferring translation scales. At the heart of our model lies a Transformer that (1) learns to balance between solved and learned pose estimations, and (2) provides a prior to guide a solver. A comprehensive analysis supports our design choices and demonstrates that our method adapts flexibly to various feature extractors and correspondence estimators, showing state-of-the-art performance in 6DoF pose estimation on Matterport3D, InteriorNet, StreetLearn, and Map-free Relocalization.
ISSN:2331-8422