Animation Video Resequencing with a Convolutional AutoEncoder

Abstract

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). SA '19 Posters, November 17-20, 2019, Brisbane, QLD, Australia © 2019 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-6943-5/19/11. https://doi.org/10.1145/3355056.3364550 animators commonly utilize a set of principles, including natural movement, as a model and will incorporate other principles for dramatic effects and emotional impact. There have been many techniques developed to ease the computer animation pipeline, production is still an arduous process that involves the creation of many image sequences depicting the motion of complex characters and their environments. If a single image is out of place, the whole animation may be ruined by an unnatural movement, which is not only visually displeasing but also distracts from the narrative.