Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner. Recent approaches to single view depth estimation explore the possibility of learning without full supervision via minimizing photometric error. In this paper, we explore the use of stereo sequences for learning depth and visual odometry. The use of stereo sequences enables the use of both spatial (between left-right pairs) and temporal (forward backward) photometric warp error, and constrains the scene depth and camera motion to be in a common, realworld scale. At test time our framework is able to estimate single view depth and two-view odometry from a monocular sequence. We also show how we can improve on a standard photometric warp loss by considering a warp of deep features. We show through extensive experiments that: (i) jointly training for single view depth and visual odometry improves depth prediction because of the additional constraint imposed on depths and achieves competitive results for visual odometry; (ii) deep feature-based warping loss improves upon simple photometric warp loss for both single view depth estimation and visual odometry. Our method outperforms existing learning based methods on the KITTI driving dataset in both tasks. The source code is available at https://github.com/Huangying-Zhan/ Depth-VO-Feat.
We present "just-in-time reconstruction" as realtime image-guided inpainting of a map with arbitrary scale and sparsity to generate a fully dense depth map for the image. In particular, our goal is to inpaint a sparse map -obtained from either a monocular visual SLAM system or a sparse sensorusing a single-view depth prediction network as a virtual depth sensor. We adopt a fairly standard approach to data fusion, to produce a fused depth map by performing inference over a novel fully-connected Conditional Random Field (CRF) which is parameterized by the input depth maps and their pixel-wise confidence weights. Crucially, we obtain the confidence weights that parameterize the CRF model in a data-dependent manner via Convolutional Neural Networks (CNNs) which are trained to model the conditional depth error distributions given each source of input depth map and the associated RGB image. Our CRF model penalises absolute depth error in its nodes and pairwise scale-invariant depth error in its edges, and the confidence-based fusion minimizes the impact of outlier input depth values on the fused result. We demonstrate the flexibility of our method by real-time inpainting of ORB-SLAM, Kinect, and LIDAR depth maps acquired both indoors and outdoors at arbitrary scale and varied amount of irregular sparsity.
PSPB accepted the recommendations of an ad hoc committee, which reviewed the policy that had previously been revised in November 2010. The highlights of the current policy are as follows: The policy reaffirms the principle that authors are free to post their own version of their IEEE periodical or conference articles on their personal Web sites, those of their employers, or their funding agencies for the purpose of meeting public availability requirements prescribed by their funding agencies. Authors may post their version of an article as accepted for publication in an IEEE periodical or conference proceedings. Posting of the final PDF, as published by IEEE Xplore®, continues to be prohibited, except for open-access journal articles supported by payment of an article processing charge (APC), whose authors may freely post the final version. The policy provides that IEEE periodicals will make available to each author a preprint version of that person's article that includes the Digital Object Identifier, IEEE's copyright notice, and a notice showing the article has been accepted for publication. The policy states that authors are allowed to post versions of their articles on approved third-party servers that are operated by not-for-profit organizations. Because IEEE policy provides that authors are free to follow public access mandates of government funding agencies, IEEE authors may follow requirements to deposit their accepted manuscripts in those government repositories.IEEE distributes accepted versions of journal articles for author posting through the Author Gateway, now used by all journals produced by IEEE Publishing Operations. (Some journals use services from external vendors, and these journals are encouraged to adopt similar services for the convenience of authors.) Authors' versions distributed through the Author Gateway include a live link to articles in IEEE Xplore. Most conferences do not use the Author Gateway; authors of conference articles should feel free to post their own version of their articles as accepted for publication by an IEEE conference, with the addition of a copyright notice and a Digital Object Identifier to the version of record in IEEE Xplore.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.