Foreground-aware Image Inpainting

TL;DR

This paper introduces a foreground-aware image inpainting method that explicitly predicts foreground contours before filling missing regions, significantly improving results especially when holes overlap with foreground objects.

Contribution

The novel approach disentangles structure inference from content completion, using contour prediction as guidance to enhance inpainting performance.

Findings

Outperforms existing inpainting methods on complex images.

Effectively handles holes overlapping with foreground objects.

Produces more realistic and coherent inpainting results.

Abstract

Existing image inpainting methods typically fill holes by borrowing information from surrounding pixels. They often produce unsatisfactory results when the holes overlap with or touch foreground objects due to lack of information about the actual extent of foreground and background regions within the holes. These scenarios, however, are very important in practice, especially for applications such as the removal of distracting objects. To address the problem, we propose a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion. Specifically, our model learns to predict the foreground contour first, and then inpaints the missing region using the predicted contour as guidance. We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting. Experiments show that our method significantly outperforms existing methods and achieves superior inpainting results on challenging cases with complex compositions.