当前位置: X-MOL 学术IEEE Access › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Perceptual-based Noise-agnostic 3D Skeleton Motion Data Refinement Network
IEEE Access ( IF 3.9 ) Pub Date : 2020-01-01 , DOI: 10.1109/access.2020.2980316
Shu-Jie Li , Hai-Sheng Zhu , Li-Ping Zheng , Lin Li

In this paper, we demonstrate a perceptual-based 3D skeleton motion data refinement method based on a bidirectional recurrent autoencoder, called BRA-P. Three main technical contributions are made by the proposed network. First, the proposed BRA-P can address noisy data with different noise types and amplitudes using one network, and this attribute makes the approach more suitable for raw motion data with heterogeneous mixed noise. Second, due to the usage of perceptual loss, which measures the difference in high-level features extracted by a pretrained perceptual autoencoder, BRA-P improves the perceptual similarity between refined motion data and clean motion data, especially for the case where the noisy data and target clean data have different topologies. Third, BRA-P further improves the bone-length consistency and smoothness of the refined motion using the perceptual autoencoder as a postprocessing network. Ablation experiments verify the effect of the three technical contributions of our approach. The results of the experiments on synthetic noise data and raw motion data captured by Kinect demonstrate that our method outperforms several state-of-the-art methods in the cleaning of mixed-noise data by one network.

中文翻译:

基于感知的噪声不可知的 3D 骨架运动数据细化网络

在本文中,我们展示了一种基于称为 BRA-P 的双向循环自动编码器的基于感知的 3D 骨骼运动数据细化方法。提议的网络做出了三个主要的技术贡献。首先,所提出的 BRA-P 可以使用一个网络处理具有不同噪声类型和幅度的噪声数据,这一属性使该方法更适合具有异构混合噪声的原始运动数据。其次,由于感知损失的使用,它测量由预训练感知自动编码器提取的高级特征的差异,BRA-P 提高了精细运动数据和干净运动数据之间的感知相似性,特别是对于噪声数据的情况和目标清洁数据具有不同的拓扑结构。第三,BRA-P 使用感知自动编码器作为后处理网络,进一步提高了精细运动的骨骼长度一致性和平滑度。消融实验验证了我们方法的三个技术贡献的效果。Kinect 捕获的合成噪声数据和原始运动数据的实验结果表明,我们的方法在通过一个网络清理混合噪声数据方面优于几种最先进的方法。
更新日期:2020-01-01
down
wechat
bug