Shuffled Autoregression for Motion Interpolation
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2023)
摘要
This work aims to provide a deep-learning solution for the motion interpolation task. Previous studies solve it with geometric weight functions. Some other works propose neural networks for different problem settings with consecutive pose sequences as input. However, motion interpolation is a more complex problem that takes isolated poses (e.g., only one start pose and one end pose) as input. When applied to motion interpolation, these deep learning methods have limited performance since they do not leverage the flexible dependencies between interpolation frames as the original geometric formulas do. To realize this interpolation characteristic, we propose a novel framework, referred to as Shuffled AutoRegression, which expands the autoregression to generate in arbitrary (shuffled) order and models any inter-frame dependencies as a directed acyclic graph. We further propose an approach to constructing a particular kind of dependency graph, with three stages assembled into an end-to-end spatial-temporal motion Transformer. Experimental results on one of the current largest datasets show that our model generates vivid and coherent motions from only one start frame to one end frame and outperforms competing methods by a large margin. The proposed model is also extensible to multiple keyframes' motion interpolation tasks and other areas' interpolation.
更多查看译文
关键词
neural networks,motion interpolation,transformer,human motion,animation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要