New at SubtleTV! Close
What to Watch

Video: Video: [SIGGRAPH 2018] Mode-Adaptive Neural Networks for Quadruped Motion Control

We present a novel method for real-time quadruped motion synthesis called Mode-Adaptive Neural Networks. Our system is trained in an end-to-end fashion on unstructured motion capture data, without requiring labels for the phase or locomotion gaits. The system can be used for creating natural animations in games and films, and is the first of such systematic approaches whose quality could be of practical use. It is implemented in the Unity 3D engine and TensorFlow, and published under the ACM Transactions on Graphics / SIGGRAPH 2018. Interactive Demo: ...will be available very soon... GitHub: Paper:
Sebastian StarkeartificialScience & TechnologyCharacter AnimationQuadrupedsNeural NetworksArtificial IntelligenceDeep LearningSIGGRAPHCharacter ControlUnity3DTensorFlowUniversity of EdinburghMotion CaptureMotion

Lola Kirke


Juliet Huddy

Carl Edwards

Jordan Hankins

Ty Pozzobon Death

Tree Man

NFL mock draft


Obama Farewell Speech

Pioneer Cabin tree

Raymond James Stadium

Alabama Vs Clemson

Clemson Tigers

Rodeo Houston 2017

Share current
Share Playlist
[SIGGRAPH 2018] Mode-Adaptive Neural Networks for Quadruped Motion Control