In advance of next month’s 43rd Siggraph Conference on Computer Graphics & Interactive Techniques here are my ‘ones-to-watch’ from the 2016 submissions that may relate to game animation in the not-so-distant future.
A Deep Learning Framework For Character Motion Synthesis And Editing
Daniel Holden, Jun Saito, Taku Komura
Starting with this presentation from the University of Edinburgh, this solution already looks like the next evolution beyond motion-matching.
“We present a framework to synthesize character movements based on high level parameters, such that the produced movements respect the manifold of human motion, trained on a large motion capture dataset.”
Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning
Xue Bin Peng, Glen Berseth, Michiel van de Panne
This next paper seeks to provide better adjustment of procedural character to adapt to complex terrain.
“…Building on recent progress in deep reinforcement learning (DeepRL), we introduce a mixture of actor-critic experts (MACE) approach that learns terrain-adaptive dynamic locomotion skills using high-dimensional state and terrain descriptions as input, and parameterized leaps or steps as output actions….”
Spectral Style Transfer for Human Motion between Independent Actions
M. Ersin Yumer, Niloy J. Mitra
Another advance on motion-synthese, this approach attempts to take motions and apply their style to others, creating entirely new actions.
“Human motion is complex and difficult to synthesize realistically. Automatic style transfer to transform the mood or identity of a character’s motion is a key technology for increasing the value of already synthesized or captured motion data…”