WSSL: Weighted Self-supervised Learning Framework For Image-inpainting

TL;DR

This paper introduces WSSL, a self-supervised learning framework for image inpainting that learns from multiple tasks and uses a combined loss function to produce more visually appealing images, outperforming previous methods.

Contribution

The paper presents a novel self-supervised learning framework with a new loss function for improved image inpainting quality.

Findings

WSSL outperforms previous image inpainting methods.

The combined loss function enhances visual quality of inpainted images.

WSSL effectively captures global image context.

Abstract

Image inpainting is the process of regenerating lost parts of the image. Supervised algorithm-based methods have shown excellent results but have two significant drawbacks. They do not perform well when tested with unseen data. They fail to capture the global context of the image, resulting in a visually unappealing result. We propose a novel self-supervised learning framework for image-inpainting: Weighted Self-Supervised Learning (WSSL) to tackle these problems. We designed WSSL to learn features from multiple weighted pretext tasks. These features are then utilized for the downstream task, image-inpainting. To improve the performance of our framework and produce more visually appealing images, we also present a novel loss function for image inpainting. The loss function takes advantage of both reconstruction loss and perceptual loss functions to regenerate the image. Our experimentation shows WSSL outperforms previous methods, and our loss function helps produce better results.