Internal Diverse Image Completion
This addresses the challenge of flexible image completion for applications like photo restoration and editing, offering a domain-agnostic solution that is incremental over single-image generative models.
The paper tackles the problem of generating diverse completions for missing regions in images without requiring large domain-specific training sets, achieving results that are competitive with or outperform existing methods on general-content images as shown in user studies and quantitative comparisons.
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.