Technical Papers

Controlling Character

Tuesday, 12 August 9:00 AM - 10:30 AM | Vancouver Convention Centre, East Building, Ballroom B-C Session Chair: Jessica Hodgins, Carnegie Mellon University

Generalizing Locomotion Style to New Animals With Inverse Optimal Regression

This paper analyzes a set of animal gaits to predict the gait of a new animal from its shape alone. The method gives realistic results on a wide range of bipeds and quadrupeds, using a novel technique that unifies inverse optimization with sparse data interpolation.

Kevin Wampler
Adobe Systems Incorporated, University of Washington

Zoran Popović
University of Washington

Jovan Popović
Adobe Systems Incorporated

Learning Bicycle Stunts

A general approach to simulation and control of a human character riding a bicycle. The rider not only learns to steer and balance in normal riding situations, but also learns to perform a wide variety of stunts, including wheelie, endo, bunny hop, front-wheel pivot, and back hop.

Jie Tan
Georgia Institute of Technology

Yuting Gu
Georgia Institute of Technology

Karen Liu
Georgia Institute of Technology

Greg Turk
Georgia Institute of Technology

Data-Driven Control of Flapping Flight

This paper presents a physically based controller that simulates the flapping behavior of a bird in flight. The simulated bird imitates life-like flapping and is interactively controllable and resilient to external disturbances.

Eunjung Ju
Samsung Electronics Co. Ltd.

Jungdam Won
Seoul National University

Jehee Lee
Seoul National University

Byungkuk Choi
Korea Advanced Institute of Science and Technology

Junyong Noh
Korea Advanced Institute of Science and Technology

Min Gyu Choi
Kwangwoon University

Online Motion Synthesis Using Sequential Monte Carlo

A novel system for synthesizing interactive and physically valid character motion based on sequential Monte Carlo sampling. The 36-degree-of-freedom 3D human character can balance, dodge projectiles, and improvise a get up strategy if forced to lose balance. No training data or state machine is needed.

Perttu Hämäläinen
Aalto University

Sebastian Eriksson
Aalto University

Esa Tanskanen
Aalto University

Ville Kyrki
Aalto University

Jaakko Lehtinen
Aalto University, NVIDIA Research

Breathing Life Into Shape: Capturing, Modeling, and Animating 3D Human Breathing

Animation of realistic breathing in virtual humans with a simple intuitive interface. Using 2,807 3D scans of 58 subjects, the technique learns a novel model of how body shape varies during breathing. Breathing-style controls and a novel spirometer interface allow "breath actors" to breathe action and emotion into a character.

Aggeliki Tsoli
Max-Planck-Institut für Intelligente Systeme

Naureen Mahmood
Max-Planck-Institut für Intelligente Systeme

Michael Black
Max-Planck-Institut für Intelligente Systeme