Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes
This work addresses the problem of generating accurate and realistic completions for corrupted images in mixed scenes, which is incremental as it builds on existing inpainting methods by incorporating semantic guidance.
The paper tackled the challenge of image inpainting for mixed scenes, where missing areas contain diverse semantic information, by proposing a Semantic Guidance and Evaluation Network (SGE-Net) that iteratively refines structural priors and inpainted images, achieving superior results in terms of clear boundaries and photo-realistic textures compared to state-of-the-art methods.
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic information, conventional two-stage approaches utilizing structural information often lead to the problem of unreliable structural prediction and ambiguous image texture generation. In this paper, we propose a Semantic Guidance and Evaluation Network (SGE-Net) to iteratively update the structural priors and the inpainted image in an interplay framework of semantics extraction and image inpainting. It utilizes semantic segmentation map as guidance in each scale of inpainting, under which location-dependent inferences are re-evaluated, and, accordingly, poorly-inferred regions are refined in subsequent scales. Extensive experiments on real-world images of mixed scenes demonstrated the superiority of our proposed method over state-of-the-art approaches, in terms of clear boundaries and photo-realistic textures.