Learning disentangling and fusing networks for face completion under structured occlusions

Zhihang Li, Yibo Hu, Ran He, Zhenan Sun

Abstract: Highlights•Face completion and corruption are treated as disentangling and fusing processes of clean faces and occlusions.•Presenting the disentangling network and fusing network for face completion and corruption under structured occlusions.•Without requiring the paired face images for training, we unify the face completion and corruption into a dual learning framework.•Experiments are performed to show the effectiveness of DF-GAN for the face completion under structured occlusions.