Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data
This addresses a specific challenge in computer vision for portrait analysis, but it is incremental as it builds on existing removal methods by adding shadow handling.
The paper tackles the problem of removing eyeglasses and their cast shadows from portrait images, which degrade face verification and expression recognition, by proposing a detect-then-remove framework that achieves this simultaneously using synthetic data and cross-domain techniques.
In portraits, eyeglasses may occlude facial regions and generate cast shadows on faces, which degrades the performance of many techniques like face verification and expression recognition. Portrait eyeglasses removal is critical in handling these problems. However, completely removing the eyeglasses is challenging because the lighting effects (e.g., cast shadows) caused by them are often complex. In this paper, we propose a novel framework to remove eyeglasses as well as their cast shadows from face images. The method works in a detect-then-remove manner, in which eyeglasses and cast shadows are both detected and then removed from images. Due to the lack of paired data for supervised training, we present a new synthetic portrait dataset with both intermediate and final supervisions for both the detection and removal tasks. Furthermore, we apply a cross-domain technique to fill the gap between the synthetic and real data. To the best of our knowledge, the proposed technique is the first to remove eyeglasses and their cast shadows simultaneously. The code and synthetic dataset are available at https://github.com/StoryMY/take-off-eyeglasses.