Render the Possibilities
the 43rd international conference and exhibition on
Computer Graphics & Interactive Techniques
24-28 July
Anaheim, California
the 43rd international conference and exhibition on
24-28 July
Anaheim, California
Showy inflorescences are a common feature of many plants. This paper presents a suite of biologically motivated algorithms for modeling inflorescences with closely packed flowers. The method accounts for neighbor-dependent floret types, petal collisions, and branching structures specific to inflorescences.
Andrew Owens
University of Calgary
Mikolaj Cieslak
University of Calgary
Jeremy Hart
University of Calgary
Regine Classen-Bockhoff
Johannes Gutenberg-Universität Mainz
Przemyslaw Prusinkiewicz
University of Calgary
Introducing a spectral style-transfer method for human motion between independent actions, thereby greatly reducing the required effort and cost of creating all-inclusive motion capture-style databases. The method leverages the spectral domain representation of the human motion to formulate a spatial-correspondence independent approach.
Mehmet Ersin Yumer
Adobe Research
Niloy Mitra
University College London
This deep learning framework for synthesizing character movements based on the user's high-level instructions uses a prior in the form of a convolutional auto-encoder trained on a large motion capture dataset.
Daniel Holden
University of Edinburgh
Jun Saito
Marza Animation Planet Inc.
Taku Komura
University of Edinburgh
A probabilistic model connecting human poses and arrangements of objects from observations of interactions collected with commodity RGB-D sensors. This model is encoded as a set of Prototypical Interaction Graphs (PiGraphs): a human-centric representation capturing physical contact and attention linkages between geometry and the human body.
Manolis Savva
Stanford University
Angel Chang
Stanford University
Pat Hanrahan
Stanford University
Matthew Fisher
Stanford University
Matthias Nießner
Stanford University