Shared May 13, 2018
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 from 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.
Windows Demo: http://www.starke-consult.de/UoE/GitH...
Linux Demo: http://www.starke-consult.de/UoE/GitH...
Mac Demo: http://www.starke-consult.de/UoE/GitH...
But what is a Neural Network? | Deep learning, chapter 1
SIGGRAPH 2018: DeepMimic paper (main video)
[SIGGRAPH 2017] A Multi-Scale Model for Simulating Liquid-Hair Interactions
Water Surface Wavelets (SIGGRAPH 2018)
Citizencon 2017: Teaching a character how to walk on any terrain
The Next Leap: How A.I. will change the 3D industry - Andrew Price
Deep Learning Cars
Adaptive Tearing and Cracking of Thin Sheets, SIGGRAPH 2014
🖥️ WRITING MY FIRST MACHINE LEARNING GAME! (1/4)
[SIGGRAPH 2018] A Multi-Scale Model for Simulating Liquid-Fabric Interactions
DeepMind's AI Learns Locomotion From Scratch | Two Minute Papers #190
Semantic Soft Segmentation (SIGGRAPH 2018)
Interlinked SPH Pressure Solvers for Strong Fluid-Rigid Coupling
[SIGGRAPH 2018] Toward Wave-based Sound Synthesis for Computer Animation
Phase-functioned neural networks for character control (SIGGRAPH 2017 Presentation)
[SIGGRAPH 2018] Animating Fluid Sediment Mixture in Particle-Laden Flows
[SIGGRAPH 2018] Moving Least Squares MPM with Compatible Particle-in-Cell
Deep Video Portraits - SIGGRAPH 2018