期刊
ROBOTICS AND AUTONOMOUS SYSTEMS
卷 171, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.robot.2023.104583
关键词
Multi-modal domain translation; Semantic perception; LiDAR
This work presents a new depth-and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation between LiDAR and camera sensors. The model is able to translate raw LiDAR point clouds to RGB-D camera images by solely relying on semantic scene segments, and it has practical applications in fields like autonomous vehicles.
This work presents a new depth-and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation in a multi-modal setup between LiDAR and camera sensors. The proposed model leverages scene semantics as a mid-level representation and is able to translate raw LiDAR point clouds to RGB-D camera images by solely relying on semantic scene segments. We claim that this is the first framework of its kind and it has practical applications in autonomous vehicles such as providing a fail-safe mechanism and augmenting available data in the target image domain. The proposed model is evaluated on the large-scale and challenging Semantic-KITTI dataset, and experimental findings show that it considerably outperforms the original TITAN-Net and other strong baselines by 23.7% margin in terms of IoU.
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