A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2003.01060v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
[article]
<span title="2020-03-28">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2020-03-02">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.01060v1">arXiv:2003.01060v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ctpxgm7vrbddpbithxznpm6tbi">fatcat:ctpxgm7vrbddpbithxznpm6tbi</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.01060v1">arXiv:2003.01060v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ctpxgm7vrbddpbithxznpm6tbi">fatcat:ctpxgm7vrbddpbithxznpm6tbi</a> </span>
We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. In particular, it aligns the training image pairs into similar lighting condition with predictive brightness transformation parameters. Besides, we model the photometric uncertainties of pixels on the
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.01060v2">arXiv:2003.01060v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ph5rwawodfhdhhx62wnmyqxjee">fatcat:ph5rwawodfhdhhx62wnmyqxjee</a>
</span>
more »
... images, which improves the depth estimation accuracy and provides a learned weighting function for the photometric residuals in direct (feature-less) visual odometry. Evaluation results show that the proposed network outperforms state-of-the-art self-supervised depth estimation networks. D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization. We evaluate D3VO in terms of monocular visual odometry on both the KITTI odometry benchmark and the EuRoC MAV dataset.The results show that D3VO outperforms state-of-the-art traditional monocular VO methods by a large margin. It also achieves comparable results to state-of-the-art stereo/LiDAR odometry on KITTI and to the state-of-the-art visual-inertial odometry on EuRoC MAV, while using only a single camera.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200401001948/https://arxiv.org/pdf/2003.01060v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.01060v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>