We consider the problem of synthesizing multi-action human motion sequences of arbitrary lengths. Existing approaches have mastered motion sequence generation in single-action scenarios, but fail to generalize to multi-action and arbitrary-length sequences. We fill this gap by proposing a novel efficient approach that leverages the expressiveness of Recurrent Transformers and generative richness of conditional Variational Autoencoders. The proposed iterative approach is able to generate smooth and realistic human motion sequences with an arbitrary number of actions and frames while doing so in linear space and time. We train and evaluate the proposed approach on PROX dataset which we augment with ground-truth action labels. Experimental evaluation shows significant improvements in FID score and semantic consistency metrics compared to the state-of-the-art.

通过 Recurrent Transformers 和条件变分自编码器的结合，我们提出了一种新的迭代式方法，能够高效地生成具有任意动作序列的人类运动序列。该方法在 PROX 和 Charades 数据集上得到了验证，表明它在 FID 得分和语义一致性指标方面显著优于现有的技术方法。

递归变压器变分自编码器用于多动作运动合成