Unsupervised domain adaptation for depth completion from sparse LiDAR scans depth map
Depth completion aims to predict the distance between objects on an image and the camera capturing the image from a LiDAR scans depth input,and the distance is expressed as a dense depth map.Denser scans depth input leads to better pre-diction,while the cost of the corresponding LiDAR equipment will be more expensive,and the model trained by dense depth input performs badly on sparse depth input.Meanwhile,it is difficult to get dense ground truth annotations for training depth completion models.To improve the performance of sparse depth input model,an unsupervised domain adaptive method is proposed.The ap-proach aligns the second-order statistics of the features generated by the convolution neural network,which is shared by dense and sparse depth input.
NETL
NSTL
万方数据
