LaFIn: Generative Landmark Guided Face Inpainting
This addresses the problem of realistic face inpainting for computer vision applications, but it is incremental as it builds on existing deep learning approaches with a specific guided strategy.
The paper tackles face inpainting in the wild by proposing LaFIn, a method that uses a landmark predictor to guide an inpainting subnet, ensuring structural and attribute consistency. It demonstrates superiority over state-of-the-art methods on CelebA-HQ and CelebA datasets, with quantitative gains, and shows that the inpainted faces can improve landmark predictor performance on 300W and WFLW datasets.
It is challenging to inpaint face images in the wild, due to the large variation of appearance, such as different poses, expressions and occlusions. A good inpainting algorithm should guarantee the realism of output, including the topological structure among eyes, nose and mouth, as well as the attribute consistency on pose, gender, ethnicity, expression, etc. This paper studies an effective deep learning based strategy to deal with these issues, which comprises of a facial landmark predicting subnet and an image inpainting subnet. Concretely, given partial observation, the landmark predictor aims to provide the structural information (e.g. topological relationship and expression) of incomplete faces, while the inpaintor is to generate plausible appearance (e.g. gender and ethnicity) conditioned on the predicted landmarks. Experiments on the CelebA-HQ and CelebA datasets are conducted to reveal the efficacy of our design and, to demonstrate its superiority over state-of-the-art alternatives both qualitatively and quantitatively. In addition, we assume that high-quality completed faces together with their landmarks can be utilized as augmented data to further improve the performance of (any) landmark predictor, which is corroborated by experimental results on the 300W and WFLW datasets.