原 CVPR2018-video object segmentation--4

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012494820/article/details/82804773

SeGAN: Segmenting and Generating the Invisible

略读，motivation

This work strives to complete the appearance of the occluded objects via two steps: segmenting the invisible parts of the objects and generating the appearance of these parts. This work combines a segmentation network and a GAN to achieve this goal.

Semantic Video Segmentation by Gated Recurrent Flow Propagation

Research Background