Foreground-aware Image Inpainting

by   Wei Xiong, et al.

Existing image inpainting methods typically fill holes by borrowing information from surrounding image regions. 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 distracting object removal. 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 this 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.


page 1

page 4

page 7

page 8


Semantic Image Inpainting with Deep Generative Models

Semantic image inpainting is a challenging task where large missing regi...

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting

In this paper, we focus on image inpainting task, aiming at recovering t...

Semantic Foreground Inpainting from Weak Supervision

Semantic scene understanding is an essential task for self-driving vehic...

Contrastive Learning for Diverse Disentangled Foreground Generation

We introduce a new method for diverse foreground generation with explici...

Information-Theoretic Segmentation by Inpainting Error Maximization

We study image segmentation from an information-theoretic perspective, p...

Automatic Semantic Content Removal by Learning to Neglect

We introduce a new system for automatic image content removal and inpain...

DeePaste – Inpainting for Pasting

One of the challenges of supervised learning training is the need to pro...

Please sign up or login with your details

Forgot password? Click here to reset