Dynamic Graph CNN for Learning on Point Clouds
Name
1801.07829.pdf
Description
Accepted version
Size
9.09 MB
Format
Adobe PDF
Checksum (MD5)
b10998e624bb2b831b9e63a2dc28e603
Author(s)
Wang, Yue
Sun, Yongbin
Liu, Ziwei
Sarma, Sanjay E
Date Issued
October 2019
Journal
ACM Transactions on Graphics
Publisher
Association for Computing Machinery (ACM)
Citation
Wang, Yue et al. "Dynamic Graph CNN for Learning on Point Clouds." ACM Transactions on Graphics 38, 5 (October 2019): 146 © 2019 The Author(s)
Version
Author's final manuscript
Abstract
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. Point clouds inherently lack topological information, so designing a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds, including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks, including ModelNet40, ShapeNetPart, and S3DIS.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Massachusetts Institute of Technology. Materials Research Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3326362
