Two papers accepted at SIGGRAPH 2021
SIGGRAPH, 9-13 August (online)
Congratulations to the computer graphics group who have had two papers accepted at SIGGRAPH 2021.
Taking place online from 9-13 August, SIGGRAPH is a premier conference & exhibition in Computer Graphics & Interactive Techniques, which celebrates the industry and its innovators.
ManipNet: Neural Manipulation Synthesis with a Hand-Object Spatial Representation
Authors: He Zhang, Yuting Ye, Takaaki Shiratori, Taku Komura
Abstract: We propose ManipNet, a deep learning framework for an interactive synthesis of detailed finger motions for dexterous hand-object manipulation.
Neural Animation Layering for Synthesizing Martial Arts Movements
Authors: Sebastian Starke, Yiwei Zhao, Fabio Zinno, Taku Komura
Abstract: We present a modular deep learning framework for animation layering to interactively synthesize novel combinations and variations from different motion skills, demonstrated on martial arts movements. Our system can be used for offline and online motion generation alike, provides an intuitive interface to integrate with animator workflows, and is relevant for real-time applications such as computer games.
IPAB Computer Graphics and Visualisation Group