PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 77 - 85
Hlavní autoři: Charles, R. Qi, Hao Su, Mo Kaichun, Guibas, Leonidas J.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.07.2017
Témata:
Computer architecture
Feature extraction
Machine learning
Semantics
Shape
Three-dimensional displays
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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, which 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.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2017.16