Self-Attention Dense Depth Estimation Network for Unrectified Video Sequences
This work addresses depth estimation for robotics and surveillance, offering an incremental improvement by adapting to unrectified images.
The paper tackles dense depth estimation from unrectified video sequences by proposing a self-attention based network that incorporates non-differentiable camera distortion into training, achieving competitive performance compared to methods using rectified images.
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.