English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose D3VO as a novel framework for monocular visual odometry thatexploits deep networks on three levels -- deep depth, pose and uncertaintyestimation. We first propose a novel self-supervised monocular depth estimationnetwork trained on stereo videos without any external supervision. Inparticular, it aligns the training image pairs into similar lighting conditionwith predictive brightness transformation parameters. Besides, we model thephotometric uncertainties of pixels on the input images, which improves thedepth estimation accuracy and provides a learned weighting function for thephotometric residuals in direct (feature-less) visual odometry. Evaluationresults show that the proposed network outperforms state-of-the-artself-supervised depth estimation networks. D3VO tightly incorporates thepredicted depth, pose and uncertainty into a direct visual odometry method toboost both the front-end tracking as well as the back-end non-linearoptimization. We evaluate D3VO in terms of monocular visual odometry on boththe KITTI odometry benchmark and the EuRoC MAV dataset.The results show thatD3VO outperforms state-of-the-art traditional monocular VO methods by a largemargin. It also achieves comparable results to state-of-the-art stereo/LiDARodometry on KITTI and to the state-of-the-art visual-inertial odometry on EuRoCMAV, while using only a single camera.

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry