Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds
Authors:
- Chris ZhangCZChris Zhang
- Wenjie LuoWLWenjie Luo
- Raquel UrtasunRURaquel Urtasun
- 1 September 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 399-408
Abstract
The following topics are dealt with: image reconstruction; learning (artificial intelligence); cameras; feature extraction; image matching; image segmentation; solid modelling; pose estimation; computer vision; stereo image processing.Keywords
This publication has 22 references indexed in Scilit:
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Fast R-CNN2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Going deeper with convolutions2015
- Fully convolutional networks for semantic segmentation2015
- Distinctive 2D and 3D features for automated large-scale scene analysis in urban areasComputers & Graphics, 2015
- Feature relevance assessment for the semantic interpretation of 3D point cloud dataISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013
- Sparse coding with an overcomplete basis set: A strategy employed by V1?Vision Research, 1997