Siggraph 2016: Top 5 Game Anim Picks

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.”

Find the complete paper here.


Task-based Locomotion

Shailen Agrawal, Michiel van de Panne

Focussing more on NPC navigation over the player, this approach prioritises footsteps for more natural motion during the all-important transitions between actions and locomotion.

“High quality locomotion is key to achieving believable character animation, but is often modeled as a generic stepping motion between two locations…”

View the paper here.


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….”

Full paper here.


Artist-Directed Dynamics For 2D Animation

Yunfei Bai, Danny M. Kaufman, C.Karen Liu, Jovan Popović

Of interest to 2D animators currently using tools like Spine, this presentation shows a fairly robust solution for getting more out of the normally rigid 2D bone driven sprite animation.

“..Artist-directed dynamics seeks to resolve this need with a unified method that combines simulation with classical keyframing techniques…”

Full paper here.


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…”

Find the full paper here.