weixin_56836871的博客

动机：Unsupervised representation learning is highly successful in natural language processing，but supervised pre-training is still dominant in computer vision. The reason may stem from differences in their respective signal spaces, Language tasks have discr

动机：propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network【CC】混合了几何特性的（就是后面的视锥模型）的自监督的单目深度估计网络创新点Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress