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 present a novel approach for unsupervised learning of depth and ego-motionfrom monocular video. Unsupervised learning removes the need for separatesupervisory signals (depth or ego-motion ground truth, or multi-view video).Prior work in unsupervised depth learning uses pixel-wise or gradient-basedlosses, which only consider pixels in small local neighborhoods. Our maincontribution is to explicitly consider the inferred 3D geometry of the scene,enforcing consistency of the estimated 3D point clouds and ego-motion acrossconsecutive frames. This is a challenging task and is solved by a novel(approximate) backpropagation algorithm for aligning 3D structures.  We combine this novel 3D-based loss with 2D losses based on photometricquality of frame reconstructions using estimated depth and ego-motion fromadjacent frames. We also incorporate validity masks to avoid penalizing areasin which no useful information exists.  We test our algorithm on the KITTI dataset and on a video dataset captured onan uncalibrated mobile phone camera. Our proposed approach consistentlyimproves depth estimates on both datasets, and outperforms the state-of-the-artfor both depth and ego-motion. Because we only require a simple video, learningdepth and ego-motion on large and varied datasets becomes possible. Wedemonstrate this by training on the low quality uncalibrated video dataset andevaluating on KITTI, ranking among top performing prior methods which aretrained on KITTI itself.

Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints