Face Image Reflection Removal
arXiv:1903.00865
Abstract
Face images captured through the glass are usually contaminated by reflections. The non-transmitted reflections make the reflection removal more challenging than for general scenes, because important facial features are completely occluded. In this paper, we propose and solve the face image reflection removal problem. We remove non-transmitted reflections by incorporating inpainting ideas into a guided reflection removal framework and recover facial features by considering 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.
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Learning Face Representation from Scratch
- FlowNet: Learning Optical Flow with Convolutional Networks
- Deep Semantic Face Deblurring
- Learning Warped Guidance for Blind Face Restoration
- UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition