arXiv (Cornell University)· 2016· Preprint
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- 2,880citations
- 2016year
Short summary
PointNet is a novel neural network architecture designed to directly process irregular 3D point cloud data, overcoming the limitations of converting it to voxel grids or images.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces PointNet, a neural network that directly processes 3D point cloud data.
- Handles permutation invariance of points, a key challenge with point cloud data.
- Achieves state-of-the-art performance in 3D classification and segmentation tasks.
- Provides theoretical analysis of the network's learning and robustness.
AI-generated from the title and abstract; the full text is not read.
Abstract
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.
The authors' abstract, as published at the source. arXiv (Cornell University), 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering