Data-driven autocompletion for keyframe animation
Data-driven autocompletion for keyframe animation
复制标题
DOI：
10.1145/3274247.3274502
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Xinyi Zhang;M. V. D. Panne
中科院分区：
文献类型：
--
作者：
Xinyi Zhang;M. V. D. Panne
我们探索从输入关键帧合成动画运动的学习自动完成方法的潜力。我们的模型使用自回归的双层递归神经网络，该网络以目标关键帧为条件。该模型是根据样本运动的运动特征和从这些运动中采样的关键帧来训练的。给定一组所需的关键帧，训练后的模型然后能够生成运动序列，这些运动序列在遵循训练语料库中观察到的示例风格的同时插入关键帧。我们在跳跃灯上演示了我们的方法，使用来自基于物理模型的不同跳跃集作为训练数据。然后，该模型可以基于不同范围的关键帧合成新的跳跃。我们详细讨论了这种方法的优点和缺点。
We explore the potential of learned autocompletion methods for synthesizing animated motions from input keyframes. Our model uses an autoregressive two-layer recurrent neural network that is conditioned on target keyframes. The model is trained on the motion characteristics of example motions and sampled keyframes from those motions. Given a set of desired key frames, the trained model is then capable of generating motion sequences that interpolate the keyframes while following the style of the examples observed in the training corpus. We demonstrate our method on a hopping lamp, using a diverse set of hops from a physics-based model as training data. The model can then synthesize new hops based on a diverse range of keyframes. We discuss the strengths and weaknesses of this type of approach in some detail.