Deep Inception Generative Network for Cognitive Image Inpainting
This work addresses image inpainting for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackled the problem of artifacts and fallacious textures in image inpainting by proposing a deep inception generative network to enhance high-level feature representation and model learning capacity, resulting in more natural image completions as shown in quantitative comparisons on datasets like ImageNet, Places2, and CelebA-HQ.
Recent advances in deep learning have shown exciting promise in filling large holes and lead to another orientation for image inpainting. However, existing learning-based methods often create artifacts and fallacious textures because of insufficient cognition understanding. Previous generative networks are limited with single receptive type and give up pooling in consideration of detail sharpness. Human cognition is constant regardless of the target attribute. As multiple receptive fields improve the ability of abstract image characterization and pooling can keep feature invariant, specifically, deep inception learning is adopted to promote high-level feature representation and enhance model learning capacity for local patches. Moreover, approaches for generating diverse mask images are introduced and a random mask dataset is created. We benchmark our methods on ImageNet, Places2 dataset, and CelebA-HQ. Experiments for regular, irregular, and custom regions completion are all performed and free-style image inpainting is also presented. Quantitative comparisons with previous state-of-the-art methods show that ours obtain much more natural image completions.