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

How would a static scene react to a local poke? What are the effects on otherparts of an object if you could locally push it? There will be distinctivemovement, despite evident variations caused by the stochastic nature of ourworld. These outcomes are governed by the characteristic kinematics of objectsthat dictate their overall motion caused by a local interaction. Conversely,the movement of an object provides crucial information about its underlyingdistinctive kinematics and the interdependencies between its parts. Thistwo-way relation motivates learning a bijective mapping between objectkinematics and plausible future image sequences. Therefore, we propose iPOKE --invertible Prediction of Object Kinematics -- that, conditioned on an initialframe and a local poke, allows to sample object kinematics and establishes aone-to-one correspondence to the corresponding plausible videos, therebyproviding a controlled stochastic video synthesis. In contrast to previousworks, we do not generate arbitrary realistic videos, but provide efficientcontrol of movements, while still capturing the stochastic nature of ourenvironment and the diversity of plausible outcomes it entails. Moreover, ourapproach can transfer kinematics onto novel object instances and is notconfined to particular object classes. Our project page is available athttps://bit.ly/3dJN4Lf.

iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis