Journal ArticleDOI
Generalizing motion edits with Gaussian processes
TLDR
This work shows that it can make motion editing more efficient by generalizing the edits an animator makes on short sequences of motion to other sequences, and predicts frames for the motion using Gaussian process models of kinematics and dynamics.Abstract:
One way that artists create compelling character animations is by manipulating details of a character's motion. This process is expensive and repetitive. We show that we can make such motion editing more efficient by generalizing the edits an animator makes on short sequences of motion to other sequences. Our method predicts frames for the motion using Gaussian process models of kinematics and dynamics. These estimates are combined with probabilistic inference. Our method can be used to propagate edits from examples to an entire sequence for an existing character, and it can also be used to map a motion from a control character to a very different target character. The technique shows good generalization. For example, we show that an estimator, learned from a few seconds of edited example animation using our methods, generalizes well enough to edit minutes of character animation in a high-quality fashion. Learning is interactive: An animator who wants to improve the output can provide small, correcting examples and the system will produce improved estimates of motion. We make this interactive learning process efficient and natural with a fast, full-body IK system with novel features. Finally, we present data from interviews with professional character animators that indicate that generalizing and propagating animator edits can save artists significant time and work.read more
Citations
More filters
Journal ArticleDOI
A Multimodal Database for Affect Recognition and Implicit Tagging
TL;DR: Results show the potential uses of the recorded modalities and the significance of the emotion elicitation protocol and single modality and modality fusion results for both emotion recognition and implicit tagging experiments are reported.
Book ChapterDOI
Generative Visual Manipulation on the Natural Image Manifold
TL;DR: This paper proposes to learn the natural image manifold directly from data using a generative adversarial neural network, and defines a class of image editing operations, and constrain their output to lie on that learned manifold at all times.
Journal ArticleDOI
The viability of crowdsourcing for survey research.
TL;DR: It is concluded that the use of these labor portals is an efficient and appropriate alternative to a university participant pool, despite small differences in personality and socially desirable responding across the samples.
Journal ArticleDOI
Coupled Dictionary Training for Image Super-Resolution
TL;DR: This paper demonstrates that the coupled dictionary learning method can outperform the existing joint dictionary training method both quantitatively and qualitatively and speed up the algorithm approximately 10 times by learning a neural network model for fast sparse inference and selectively processing only those visually salient regions.
Journal ArticleDOI
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid
Gary K. L. Tam,Zhi-Quan Cheng,Yu-Kun Lai,Frank C. Langbein,Yonghuai Liu,David Marshall,Ralph R. Martin,Xianfang Sun,Paul L. Rosin +8 more
TL;DR: This study serves to give a comprehensive survey of both types of registration, focusing on three-dimensional point clouds and meshes, and shows how overfitting arises in nonrigid registration and the reasons for increasing interest in intrinsic techniques.
References
More filters
Book
Gaussian Processes for Machine Learning
TL;DR: The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics, and deals with the supervised learning problem for both regression and classification.
Proceedings ArticleDOI
Motion graphs
TL;DR: This paper presents a novel method for creating realistic, controllable motion given a corpus of motion capture data, and presents a general framework for extracting particular graph walks that meet a user's specifications.
Proceedings ArticleDOI
Interactive control of avatars animated with human motion data
TL;DR: This paper shows that a motion database can be preprocessed for flexibility in behavior and efficient search and exploited for real-time avatar control and demonstrates the flexibility of the approach through four different applications.
Proceedings ArticleDOI
Retargetting motion to new characters
TL;DR: In this article, a spacetime constraints solver computes an adapted motion that re-establishes these constraints while preserving the frequency characteristics of the original signal, and demonstrate their approach on motion capture data.
Journal ArticleDOI
Verbs and adverbs: multidimensional motion interpolation
TL;DR: A system for real-time interpolated animation that addresses some of the problems of simulated figures that alter their actions based on their momentary mood or in response to changes in their goals or environmental stimuli.