3 Hits in 3.8 sec


Zihao Yan, Ruizhen Hu, Xingguang Yan, Luanmin Chen, Oliver Van Kaick, Hao Zhang, Hui Huang
2019 ACM Transactions on Graphics  
We introduce RPM-Net, a deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D point cloud shape.  ...  We show results of simultaneous motion and part predictions from synthetic and real scans of 3D objects exhibiting a variety of part mobilities, possibly involving multiple movable parts.  ...  CONCLUSION AND FUTURE WORK We introduced RPM-Net, a recurrent deep network that predicts the motion of shape parts, effectively partitioning an input point cloud into a reference part and one or more moving  ... 
doi:10.1145/3355089.3356573 fatcat:r5a3u6hrorf27ivajz2ji2vorq

Self-Supervised Learning of Part Mobility from Point Cloud Sequence [article]

Yahao Shi, Xinyu Cao, Bin Zhou
2021 arXiv   pre-print
In this study, we introduce a self-supervised method for segmenting motion parts and predicting their motion attributes from a point cloud sequence representing a dynamic object.  ...  To the best of our knowledge, this is the first study on deep learning to extract part mobility from point cloud sequence of a dynamic object.  ...  This work was supported in part by National Key Research and Development Program of China (2018YFC0831003 and 2019YFF0302902), National Natural Science Foundation of China (61902014 and U1736217 and 61932003  ... 
arXiv:2010.11735v2 fatcat:sark7grxmvgmxfmceajpbbabh4

Deep Learning for 3D Point Cloud Understanding: A Survey [article]

Haoming Lu, Humphrey Shi
2021 arXiv   pre-print
The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding.  ...  To demonstrate the latest progress of deep learning for 3D point cloud understanding, this paper summarizes recent remarkable research contributions in this area from several different directions (classification  ...  RPM-Net [125] inherits the idea of RPM [27] algorithm, and takes advantage of deep learning to enhance robustness against noise, outliers and bad initialization.  ... 
arXiv:2009.08920v2 fatcat:qiuhs6v345bpffzjk2nvhgbfvq