👉[Preprint]:point_left:

Motion completion is a challenging and long-discussed problem, which is of great significance in film and game applications. For different motion completion scenarios (in-betweening, in-filling, and blending), most previous methods deal with the completion problems with case-by-case 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 under multiple evaluation settings. Inspired by the recent great success of attention-based models, we consider the completion as a sequence to sequence prediction problem. Our method consists of two modules - a standard transformer encoder with self-attention that learns long-range dependencies of input motions, and a trainable mixture embedding module that models temporal information and discriminates key-frames. Our method can run in a non-autoregressive manner and predict multiple missing frames within a single forward propagation in real time. We finally show the effectiveness of our method in music-dance applications.

With the help of Transformer, we achieve a new SOTA result on Lafan1 dataset.

• Some results (blue appearaces represent keyframes):

We also evaluate our method on the Anidance dataset:

• Infilling on the test set (black skeletons are the keyframes):

(From Left to Right: Ours, Interp. and Ground Truth)

• Infilling on random keyframes (keyframes are randomly chosen from the test set with a random order for simulating in-the-wild scenario):

(From Left to Right: Ours, Interp. and Ground Truth)

Our method can also work on complex dance movement completion:

Coming soon

@misc{duan2021singleshot,
      title={Single-Shot Motion Completion with Transformer}, 
      author={Yinglin Duan and Tianyang Shi and Zhengxia Zou and Yenan Lin and Zhehui Qian and Bohan Zhang and Yi Yuan},
      year={2021},
      eprint={2103.00776},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}