Face Image Reflection Removal
This addresses the challenge of reflection removal specifically for face images, which is important for applications like face recognition, but it appears incremental as it builds on existing guided frameworks and inpainting ideas.
The paper tackles the problem of removing reflections from face images captured through glass, which occlude facial features, by incorporating inpainting ideas and face-specific priors into a guided framework. The method shows advantages in improving face recognition compared to state-of-the-art methods, as demonstrated on a newly collected dataset.
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.