Holistic 3d Scene Understanding From A Single Geo-Tagged Image
CVPR(2015)
摘要
In this paper we are interested in exploiting geographic priors to help outdoor scene understanding. Towards this goal we propose a holistic approach that reasons jointly about 3D object detection, pose estimation, semantic segmentation as well as depth reconstruction from a single image. Our approach takes advantage of large-scale crowd sourced maps to generate dense geographic, geometric and semantic priors by rendering the 3D world. We demonstrate the effectiveness of our holistic model on the challenging KITTI dataset [13], and show significant improvements over the baselines in all metrics and tasks.
更多查看译文
关键词
holistic 3D scene understanding,geo-tagged image,geographic priors,outdoor scene understanding,3D object detection,pose estimation,semantic segmentation,depth reconstruction,geometric prior,semantic prior,3D world rendering,KITTI dataset
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络