期刊
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
卷 -, 期 -, 页码 5880-5886出版社
IEEE
DOI: 10.1109/icra.2019.8794404
关键词
-
资金
- MOST Joint Research Center for AI Technology [MOST 108-2634-F-007-006, MOST-108-2636-E-009-001]
- MOST All Vista Healthcare [MOST 108-2634-F-007-006, MOST-108-2636-E-009-001]
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据