Face image reflection removal

• Main Authors: Wan, Renjie, Shi, Boxin, Li, Haoliang, Duan, Ling-Yu, Kot, Alex Chichung
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Electrical and electronic engineering; Reflection Removal; Deep Learning
• Online Access: https://hdl.handle.net/10356/160951
• Institution: Nanyang Technological University

Face images captured through glass are usually contaminated by reflections. The low-transmitted reflections make the reflection removal more challenging than for general scenes because important facial features would be completely occluded. In this paper, we propose and solve the face image reflection removal problem. We recover the important facial structures by incorporating inpainting ideas into a guided reflection removal framework, which takes two images as the input and considers various face-specific priors. We use a newly collected face reflection image dataset to train our model and compare with state-of-the-art methods. The proposed method shows advantages in estimating reflection-free face images for improving face recognition.