Internal Diverse Image Completion

TL;DR

This paper introduces Internal Diverse Completion (IDC), a novel image completion method that generates diverse results without needing training data, effective on any image domain by leveraging multi-scale information from a single image.

Contribution

The paper presents a training-free, single-image based diverse image completion method that adapts multi-scale generative models for arbitrary images.

Findings

Effective on various datasets

Outperforms existing methods in diversity and quality

Validated through user studies and quantitative metrics

Abstract

Image completion is widely used in photo restoration and editing applications, e.g. for object removal. Recently, there has been a surge of research on generating diverse completions for missing regions. However, existing methods require large training sets from a specific domain of interest, and often fail on general-content images. In this paper, we propose a diverse completion method that does not require a training set and can thus treat arbitrary images from any domain. Our internal diverse completion (IDC) approach draws inspiration from recent single-image generative models that are trained on multiple scales of a single image, adapting them to the extreme setting in which only a small portion of the image is available for training. We illustrate the strength of IDC on several datasets, using both user studies and quantitative comparisons.