DPC-Net: Deep Pose Correction for Visual Localization

Abstract

We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a deep network, we propose an approach that uses a convolutional neural network to learn difficult-to-model corrections to the estimator from ground-truth training data. To this end, we derive a novel loss function for learning SE(3) corrections based on a matrix Lie groups approach, with a natural formulation for balancing translation and rotation errors. We use this loss to train a Deep Pose Correction network (DPC-Net) that predicts corrections for a particular estimator, sensor and environment. Using the KITTI odometry dataset, we demonstrate significant improvements to the accuracy of a computationally-efficient sparse stereo visual odometry pipeline, that render it as accurate as a modern computationally-intensive dense estimator. Further, we show how DPC-Net can be used to mitigate the effect of poorly calibrated lens distortion parameters.

In IEEE Robotics and Automation Letters (RA-L) and presented at the IEEE International Conference on Robotics and Automation (ICRA'18), Brisbane, Australia, May 21-25, 2018

References in corpus (4)

• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change
• PROBE-GK: Predictive Robust Estimation using Generalized Kernels
• PROBE: Predictive Robust Estimation for Visual-Inertial Navigation

Cited by in corpus (14)

• Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas
• A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty
• Self-Supervised Deep Pose Corrections for Robust Visual Odometry
• The Complex-Step Derivative Approximation on Matrix Lie Groups
• Learning Matchable Image Transformations for Long-term Metric Visual Localization
• Probabilistic Regression of Rotations using Quaternion Averaging and a Deep Multi-Headed Network
• Online Learning of Wheel Odometry Correction for Mobile Robots with Attention-based Neural Network
• Information-Theoretic Odometry Learning
• Machine Vision in the Context of Robotics: A Systematic Literature Review
• Exploring Self-Attention for Visual Odometry
• DRF: A Framework for High-Accuracy Autonomous Driving Vehicle Modeling
• Improving GNSS Positioning using Neural Network-based Corrections
• RAM-VO: Less is more in Visual Odometry
• Deep Inertial Odometry with Accurate IMU Preintegration