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

Optical Flow (OF) and depth are commonly used for visual odometry since theyprovide sufficient information about camera ego-motion in a rigid scene. Wereformulate the problem of ego-motion estimation as a problem of motionestimation of a 3D-scene with respect to a static camera. The entire scenemotion can be represented as a combination of motions of its visible points.Using OF and depth we estimate a motion of each point in terms of 6DoF andrepresent results in the form of motion maps, each one addressing single degreeof freedom. In this work we provide motion maps as inputs to a deep neuralnetwork that predicts 6DoF of scene motion. Through our evaluation on outdoorand indoor datasets we show that utilizing motion maps leads to accuracyimprovement in comparison with naive stacking of depth and OF. Anothercontribution of our work is a novel network architecture that efficientlyexploits motion maps and outperforms learnable RGB/RGB-D baselines.

Scene Motion Decomposition for Learnable Visual Odometry