Image Inpainting using Partial Convolution

TL;DR

This paper introduces a deep learning approach for image inpainting utilizing partial convolution layers to effectively restore corrupted or missing regions in images.

Contribution

It proposes a novel deep learning method employing partial convolution layers specifically designed for robust image inpainting tasks.

Findings

Partial convolution improves inpainting quality in corrupted images.

The method outperforms traditional techniques in restoring missing regions.

Deep learning with partial convolution achieves more realistic inpainting results.

Abstract

Image Inpainting is one of the very popular tasks in the field of image processing with broad applications in computer vision. In various practical applications, images are often deteriorated by noise due to the presence of corrupted, lost, or undesirable information. There have been various restoration techniques used in the past with both classical and deep learning approaches for handling such issues. Some traditional methods include image restoration by filling gap pixels using the nearby known pixels or using the moving average over the same. The aim of this paper is to perform image inpainting using robust deep learning methods that use partial convolution layers.