Combining Scene Coordinate Regression and Absolute Pose Regression for Visual Relocalization

Jiahao Ruan1; Li He2; Yisheng Guan1; Hong Zhang2

10.1109/ICRA48891.2023.10160317

2023-05-29

IEEE International Conference on Robotics and Automation (ICRA)

1050-4729

2577-087X

979-8-3503-2366-5

2023 IEEE International Conference on Robotics and Automation (ICRA)

2023-May

11749-11755

29 May-2 June 2023

London, United Kingdom

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Visual relocalization is a fundamental problem in computer vision and robotics. Recently, regression-based methods become popular and they can be categorized into two classes: absolute pose regression and scene coordinate regression. In this work, we present a combined regression network that jointly learns scene coordinate regression and absolute pose regression for single-image visual relocalization. The proposed network composes of a feature encoder and two regression branches with uncertainty modeling. In particular, we design a deep feature conditioning module, aiming at propagating the coarse pose information in absolute pose regression to inform the predictions in scene coordinate regression. The proposed network is trained in an end-to-end fashion to learn both regression tasks. Moreover, we propose an uncertainty-driven RANSAC algorithm that incorporates the predicted scene coordinates and their uncertainties to solve the camera pose during inference. To the best of our knowledge, this work is the first to combine scene coordinate regression and pose regression in a hierarchical framework for visual relocalization. Experiments on indoor and outdoor benchmarks demonstrate the effectiveness and the superiority of the proposed method over the state-of-the-art methods.

Visualization Computer vision Uncertainty Robot kinematics Benchmark testing Predictive models Prediction algorithms

其他

英语

CPCI-S ; EI

Pearl River Talent Recruitment Program[2019QN01X761]

Automation & Control Systems ; Computer Science ; Engineering ; Robotics

Automation & Control Systems ; Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Robotics

WOS:001048371103121

20233514632979

Inference engines ; Regression analysis ; Uncertainty analysis

Expert Systems:723.4.1 ; Computer Applications:723.5 ; Vision:741.2 ; Probability Theory:922.1 ; Mathematical Statistics:922.2

IEEE

1.School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China
2.Department of Electrical and Electronic Engineering, Shenzhen Key - Laboratory of Robotics and Computer Vision, Southern University of Science and Technology, Shenzhen, China

Jiahao Ruan,Li He,Yisheng Guan,et al. Combining Scene Coordinate Regression and Absolute Pose Regression for Visual Relocalization[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023:11749-11755.