Skip to content

Dynamic Graph CNN for Learning on Point Clouds

Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay Emani Sarma, Michael M. Bronstein, Justin Solomon

ACM Transactions on Graphics · 2019 · 7,568 citationsOpen access

No retraction on record in OpenAlex.Check Crossref now

Cite this paper

Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. (2019). Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics, 38(5), 1–12. https://doi.org/10.1145/3326362

In text: (Wang et al., 2019)

Ask a question about this research

One question, free, no account. Anchorcite finds the papers, checks each against Crossref and links every sentence of the answer to the passage it comes from.

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.

  1. Deep Residual Learning for Image Recognition2016
  2. ImageNet classification with deep convolutional neural networks2017
  3. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks2016
  4. You Only Look Once: Unified, Real-Time Object Detection2016
  5. Going deeper with convolutions2015

Metadata from OpenAlex (CC0). Citations are generated from the published record.