.png){kind=icon}
返回
Supervoxel Convolution for Online 3D Semantic Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1145/3453485.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Online 3D semantic segmentation, which aims to perform real-time 3D scene reconstruction along with semantic segmentation, is an important but challenging topic. A key challenge is to strike a balance between efficiency and segmentation accuracy. There are very fewdeep-learning-based solutions to this problem, since the commonly used deep representations based on volumetric-grids or points do not provide efficient 3D representation and organization structure for online segmentation. Observing that on-surface supervoxels, i.e., clusters of on-surface voxels, provide a compact representation of 3D surfaces and brings efficient connectivity structure via supervoxel clustering, we explore a supervoxel-based deep learning solution for this task. To this end, we contribute a novel convolution operation (SVConv) directly on supervoxels. SVConv can efficiently fuse the multi-view 2D features and 3D features projected on supervoxels during the online 3D reconstruction, and leads to an effective supervoxel-based convolutional neural network, termed as Supervoxel-CNN, enabling 2D-3D joint learning for 3D semantic prediction. With the Supervoxel-CNN, we propose a clustering-then-prediction online 3D semantic segmentation approach. The extensive evaluations on the public 3D indoor scene datasets show that our approach significantly outperforms the existing online semantic segmentation systems in terms of efficiency or accuracy.
Keyword:
Depth fusion
semantic mapping
supervoxel clustering
supervoxel convolution
deep learning
期刊
IF:
9.5
论文数:
4.8K
被引数:
3.6W
机构
引用论文
分享收藏Improving the Thermal Comfort of an Open Space via Landscape Design: A Case Study in Hot and Humid Areas.png)
Atmosphere
OAAI
AtmosphereIF0
OAAI分享收藏
Performance of the general circulation models in simulating temperature and precipitation over Iran
PREAI
分享收藏
查看更多内容