Learning 3D Semantic Segmentation with only 2D Image Supervision
2021 International Conference on 3D Vision (3DV)(2021)
摘要
With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth 3D semantic segmentation annotations are limited in both quantity and geographic diversity, while also being difficult to transfer across sensors. In contrast,...
更多查看译文
关键词
Training,Image segmentation,Solid modeling,Three-dimensional displays,Laser radar,Semantics,Urban areas
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要