Geometric Consistency for Self-Supervised End-to-End Visual Odometry

Iyer, Ganesh; Murthy, J. Krishna; Gupta, Gunshi; Krishna, K. Madhava; Paull, Liam

doi:10.48550/arxiv.1804.03789

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, such a pairwise photometric consistency constraint is very noisy due to illumination variation, low texture, occlusion, etc. Recently, Iyer et al [13] proposed a composite transformation constraint for self-supervised visual odometry learning. By combining the pairwise image reconstruction constraint with the composite transformation constraint, we propose a multi-view image reprojection constraint that is robust to noise and provides strong self-supervision for our multi-view depth and visual odometry learning.…”

Section: Multi-view Reprojection Lossmentioning

confidence: 99%

Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth

Wang

Pizer

Frahm

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

187

112

View full text Add to dashboard Cite

Deep learning-based, single-view depth estimation methods have recently shown highly promising results. However, such methods ignore one of the most important features for determining depth in the human vision system, which is motion. We propose a learning-based, multiview dense depth map and odometry estimation method that uses Recurrent Neural Networks (RNN) and trains utilizing multi-view image reprojection and forward-backward flowconsistency losses. Our model can be trained in a supervised or even unsupervised mode. It is designed for depth and visual odometry estimation from video where the input frames are temporally correlated. However, it also generalizes to single-view depth estimation. Our method produces superior results to the state-of-the-art approaches for single-view and multi-view learning-based depth estimation on the KITTI driving dataset. Fully Convolutional LSTM network Fully Convolutional LSTM network Learning parameters with shared weights

show abstract

Section: Multi-view Reprojection Lossmentioning

confidence: 99%

Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth

Wang

Pizer

Frahm

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

187

112

View full text Add to dashboard Cite

show abstract

“…VO can be used to estimate the poses of robots and unmanned vehicles by using only cameras. In the past few decades, it has caused widespread concern in the robotics and driverless industries [1], [2]. Among them, feature-based methods and direct methods have achieved great success.…”

Section: Introductionmentioning

confidence: 99%

MagicVO: An End-to-End Hybrid CNN and Bi-LSTM Method for Monocular Visual Odometry

Jiao

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

For the robotic positioning and navigation, visual odometry (VO) system is widely used. However, the errors of the traditional VO accumulate when the robot moves. Besides, this paper proposes a new framework to solve the problem of monocular VO, called MagicVO. Based on the convolutional neural network (CNN) and the bi-directional LSTM (Bi-LSTM), MagicVO outputs a 6-DoF absolute-scale pose at each position of the camera with a sequence of continuous monocular images as input. It does not only utilize the outstanding performance of CNN in extracting the rich features of image frames fully but also learns the geometric relationship from image sequences pre and post through Bi-LSTM to get a more accurate prediction. A pipeline of the MagicVO is shown in this paper. The MagicVO is an end-to-end system, and the results of the experiments on the KITTI and ETH datasets show that MagicVO has a better performance than the traditional VO systems in the accuracy of pose and the generalization ability.

show abstract

Geometric Consistency for Self-Supervised End-to-End Visual Odometry

Cited by 2 publications

References 0 publications

Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth

Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth

MagicVO: An End-to-End Hybrid CNN and Bi-LSTM Method for Monocular Visual Odometry

Contact Info

Product

Resources

About