![]() Neural Animation Layering for Synthesizing Martial Arts Movements We demonstrate that the learned periodic embedding can significantly help to improve neural motion synthesis in a number of tasks, including diverse locomotion skills, style-based movements, dance motion synthesis from music, synthesis of dribbling motions in football, and motion query for matching poses within large animation databases. Our method extracts a multi-dimensional phase space from full-body motion data, which effectively clusters animations and produces a manifold in which computed feature distances provide a better similarity measure than in the original motion space to achieve better temporal and spatial alignment. The character movements are decomposed into multiple latent channels that capture the non-linear periodicity of different body segments while progressing forward in time. In this work, we propose a novel neural network architecture called the Periodic Autoencoder that can learn periodic features from large unstructured motion datasets in an unsupervised manner. Learning the spatial-temporal structure of body movements is a fundamental problem for character motion synthesis. ![]() Further advances on this research will continue being added to this project.ĭeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds ![]() This repository demonstrates using neural networks for animating biped locomotion, quadruped locomotion, and character-scene interactions with objects and the environment, plus sports and fighting games. Over the last couple years, this project has become a comprehensive framework for data-driven character animation, including data processing, network training and runtime control, developed in Unit圓D / Tensorflow / PyTorch. research at the University of Edinburgh in the School of Informatics, supervised by Taku Komura. ![]() This project explores the opportunities of deep learning for character animation and control as part of my Ph.D. AI4Animation: Deep Learning for Character Control
0 Comments
Leave a Reply. |