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 method for simultaneous learning of depth, egomotion,object motion, and camera intrinsics from monocular videos, using onlyconsistency across neighboring video frames as supervision signal. Similarly toprior work, our method learns by applying differentiable warping to frames andcomparing the result to adjacent ones, but it provides several improvements: Weaddress occlusions geometrically and differentiably, directly using the depthmaps as predicted during training. We introduce randomized layer normalization,a novel powerful regularizer, and we account for object motion relative to thescene. To the best of our knowledge, our work is the first to learn the cameraintrinsic parameters, including lens distortion, from video in an unsupervisedmanner, thereby allowing us to extract accurate depth and motion from arbitraryvideos of unknown origin at scale. We evaluate our results on the Cityscapes,KITTI and EuRoC datasets, establishing new state of the art on depth predictionand odometry, and demonstrate qualitatively that depth prediction can belearned from a collection of YouTube videos.

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras