English

Shuffled Autoregression For Motion Interpolation

Computer Vision and Pattern Recognition 2023-06-13 v1 Artificial Intelligence

Abstract

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 \emph{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.

Keywords

Cite

@article{arxiv.2306.06367,
  title  = {Shuffled Autoregression For Motion Interpolation},
  author = {Shuo Huang and Jia Jia and Zongxin Yang and Wei Wang and Haozhe Wu and Yi Yang and Junliang Xing},
  journal= {arXiv preprint arXiv:2306.06367},
  year   = {2023}
}

Comments

accepted by ICASSP 2023

R2 v1 2026-06-28T11:01:49.341Z