arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.06397cs.CVcs.RO
收藏

DFineNet:在RGB指导下从稀疏、噪声深度输入进行自我运动估计和深度细化

DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance

University of Pennsylvania(宾夕法尼亚大学)

Yilun Zhang, Ty Nguyen, Ian D. Miller, Shreyas S. Shivakumar, Steven Chen, Camillo J. Taylor, Vijay Kumar

摘要:

深度估计是自主车辆理解和重建3D环境以及在执行期间避开障碍物的重要能力。精确的深度传感器(例如LiDAR)通常是重的、昂贵的,并且只能提供稀疏的深度,而较轻的深度传感器(例如立体相机)相比之下噪声较大。我们提出了一种端到端的学习算法,它能够使用稀疏的、有噪声的输入深度进行细化和深度完成。我们的模型还生成相机姿势作为副产品,使其成为自主系统的绝佳解决方案。我们在室内和室外数据集上评估了我们的方法。实验结果表明,该方法在KITTI~ \cite{kitti_geiger2012we}数据集上表现良好,在TUM~ \cite{sturm12iros}数据集上具有较好的稀疏、噪声输入深度处理性能.

英文摘要:

Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution. Accurate depth sensors such as LiDARs are often heavy, expensive and can only provide sparse depth while lighter depth sensors such as stereo cameras are noiser in comparison. We propose an end-to-end learning algorithm that is capable of using sparse, noisy input depth for refinement and depth completion. Our model also produces the camera pose as a byproduct, making it a great solution for autonomous systems. We evaluate our approach on both indoor and outdoor datasets. Empirical results show that our method performs well on the KITTI~\cite{kitti_geiger2012we} dataset when compared to other competing methods, while having superior performance in dealing with sparse, noisy input depth on the TUM~\cite{sturm12iros} dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑