A Unified Framework for Real Time Motion Completion
Keywords:Domain(s) Of Application (APP), Machine Learning (ML)
AbstractMotion completion, as a challenging and fundamental problem, is of great significance in film and game applications. For different motion completion application scenarios (in-betweening, in-filling, and blending), most previous methods deal with the completion problems with case-by-case methodology designs. In this work, we propose a simple but effective method to solve multiple motion completion problems under a unified framework and achieves a new state-of-the-art accuracy on LaFAN1 (+17% better than previous sota) under multiple evaluation settings. Inspired by the recent great success of self-attention-based transformer models, we consider the completion as a sequence-to-sequence prediction problem. Our method consists of three modules - a standard transformer encoder with self-attention that learns long-range dependencies of input motions, a trainable mixture embedding module that models temporal information and encodes different key-frame combinations in a unified form, and a new motion perceptual loss for better capturing high-frequency movements. Our method can predict multiple missing frames within a single forward propagation in real-time and get rid of the post-processing requirement. We also introduce a novel large-scale dance movement dataset for exploring the scaling capability of our method and its effectiveness in complex motion applications.
How to Cite
Duan, Y., Lin, Y., Zou, Z., Yuan, Y., Qian, Z., & Zhang, B. (2022). A Unified Framework for Real Time Motion Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4459-4467. https://doi.org/10.1609/aaai.v36i4.20368
AAAI Technical Track on Domain(s) Of Application