In this paper we present a learned alternative to the Motion Matching algorithm which retains the positive properties of Motion Matching but additionally achieves the scalability of neural-network-based generative models. Although neural-network-based generative models for character animation are capable of learning expressive, compact controllers from vast amounts of animation data, methods such as Motion Matching still remain a popular choice in the games industry due to their flexibility, predictability, low preprocessing time, and visual quality - all properties which can sometimes be difficult to achieve with neural-network-based methods. Yet, unlike neural networks, the memory usage of such methods generally scales linearly with the amount of data used, resulting in a constant trade-off between the diversity of animation which can be produced and real world production budgets. In this work we combine the benefits of both approaches and, by breaking down the Motion Matching algorithm into its individual steps, show how learned, scalable alternatives can be used to replace each operation in turn. Our final model has no need to store animation data or additional matching meta-data in memory, meaning it scales as well as existing generative models. At the same time, we preserve the behavior of Motion Matching, retaining the quality, control, and quick iteration time which are so important in the industry.
We present a method for reconstructing the global position of motion capture where position sensing is poor or unavailable. Capture systems, such as IMU suits, can provide excellent pose and orientation data of a capture subject, but otherwise need post processing to estimate global position. We propose a solution that trains a neural network to predict, in real-time, the height and body displacement given a short window of pose and orientation data. Our training dataset contains pre-recorded data with global positions from many different capture subjects, performing a wide variety of activities in order to broadly train a network to estimate on like and unseen activities. We compare training on two network architectures, a universal network (u-net) and a traditional convolutional neural network (CNN) - observing better error properties for the u-net in our results. We also evaluate our method for different classes of motion. We observe high quality results for motion examples with good representation in specialized datasets, while general performance appears better in a more broadly sampled dataset when input motions are far from training examples.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.