论文标题
未经启动的视频序列的自我发作密集的深度估计网络
Self-Attention Dense Depth Estimation Network for Unrectified Video Sequences
论文作者
论文摘要
3D场景的密集深度估计具有许多应用，主要用于机器人技术和监视。 LIDAR和雷达传感器是实时深度估计的硬件解决方案，但是这些传感器会产生稀疏的深度图，有时不可靠。近年来，旨在使用单2D图像来解决深度估算的研究受到了很多关注。基于深度学习的自我监督深度估计方法来自整流的立体声和单眼视频帧，已显示出令人鼓舞的结果。我们建议一个基于自我注意力的深度和自我运动网络，以实现未经启动的图像。我们还将摄像机的非差异变形引入训练管道。与其他使用整流图像进行深度估计的既定方法相比，我们的方法具有竞争力。
The dense depth estimation of a 3D scene has numerous applications, mainly in robotics and surveillance. LiDAR and radar sensors are the hardware solution for real-time depth estimation, but these sensors produce sparse depth maps and are sometimes unreliable. In recent years research aimed at tackling depth estimation using single 2D image has received a lot of attention. The deep learning based self-supervised depth estimation methods from the rectified stereo and monocular video frames have shown promising results. We propose a self-attention based depth and ego-motion network for unrectified images. We also introduce non-differentiable distortion of the camera into the training pipeline. Our approach performs competitively when compared to other established approaches that used rectified images for depth estimation.
