Semantics-Guided Object Removal for Facial Images: with Broad Applicability and Robust Style Preservation
This work solves the incremental problem of improving facial image inpainting for applications like photo editing and forensics, by combining strengths of prior methods.
The paper tackles the problem of object removal and inpainting in facial images, where existing methods trade off between style consistency and detail preservation. The proposed Semantics-Guided Inpainting Network (SGIN) addresses this by modifying a modulated generator with semantic guidance, achieving improved performance in handling various mask sizes while maintaining style and details.
Object removal and image inpainting in facial images is a task in which objects that occlude a facial image are specifically targeted, removed, and replaced by a properly reconstructed facial image. Two different approaches utilizing U-net and modulated generator respectively have been widely endorsed for this task for their unique advantages but notwithstanding each method's innate disadvantages. U-net, a conventional approach for conditional GANs, retains fine details of unmasked regions but the style of the reconstructed image is inconsistent with the rest of the original image and only works robustly when the size of the occluding object is small enough. In contrast, the modulated generative approach can deal with a larger occluded area in an image and provides {a} more consistent style, yet it usually misses out on most of the detailed features. This trade-off between these two models necessitates an invention of a model that can be applied to any size of mask while maintaining a consistent style and preserving minute details of facial features. Here, we propose Semantics-Guided Inpainting Network (SGIN) which itself is a modification of the modulated generator, aiming to take advantage of its advanced generative capability and preserve the high-fidelity details of the original image. By using the guidance of a semantic map, our model is capable of manipulating facial features which grants direction to the one-to-many problem for further practicability.