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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we propose a novel self-supervised learning model forestimating continuous ego-motion from video. Our model learns to estimatecamera motion by watching RGBD or RGB video streams and determiningtranslational and rotation velocities that correctly predict the appearance offuture frames. Our approach differs from other recent work on self-supervisedstructure-from-motion in its use of a continuous motion formulation andrepresentation of rigid motion fields rather than direct prediction of cameraparameters. To make estimation robust in dynamic environments with multiplemoving objects, we introduce a simple two-component segmentation process thatisolates the rigid background environment from dynamic scene elements. Wedemonstrate state-of-the-art accuracy of the self-trained model on severalbenchmark ego-motion datasets and highlight the ability of the model to providesuperior rotational accuracy and handling of non-rigid scene motions.

CeMNet: Self-supervised learning for accurate continuous ego-motion estimation