Your browser doesn't support javascript.
Mask removal : Face inpainting via attributes.
Jiang, Yefan; Yang, Fan; Bian, Zhangxing; Lu, Changsheng; Xia, Siyu.
  • Jiang Y; Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, 210096 People's Republic of China.
  • Yang F; College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China.
  • Bian Z; Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI USA.
  • Lu C; College of Engineering and Computer Science, The Australian National University, Canberra, Australia.
  • Xia S; Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, 210096 People's Republic of China.
Multimed Tools Appl ; 81(21): 29785-29797, 2022.
Article in English | MEDLINE | ID: covidwho-1990723
ABSTRACT
Due to the outbreak of the COVID-19 pandemic, wearing masks in public areas has become an effective way to slow the spread of disease. However, it also brings some challenges to applications in daily life as half of the face is occluded. Therefore, the idea of removing masks by face inpainting appeared. Face inpainting has achieved promising performance but always fails to guarantee high-fidelity. In this paper, we present a novel mask removal inpainting network based on face attributes known in advance including nose, chubby, makeup, gender, mouth, beard and young, aiming to ensure the repaired face image is closer to ground truth. To achieve this, a dual pipeline network based on GANs has been proposed, one of which is a reconstructive path used in training that utilizes missing regions in ground truth to get prior distribution, while the other is a generative path for predicting information in the masked region. To establish the process of mask removal, we build a synthetic facial occlusion that mimics the real mask. Experiments show that our method not only generates faces more similarly aligned with real attributes, but also ensures semantic and structural rationality compared with state-of-the-art methods.
Keywords

Full text: Available Collection: International databases Database: MEDLINE Type of study: Prognostic study Language: English Journal: Multimed Tools Appl Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Type of study: Prognostic study Language: English Journal: Multimed Tools Appl Year: 2022 Document Type: Article