Painting Outside as Inside: Edge Guided Image Outpainting via Bidirectional Rearrangement with Progressive Step Learning

Understand

Image outpainting is a very intriguing problem as the outside of a given image can be continuously filled by considering as the context of the image.

• This task has two main challenges.
• The first is to maintain the spatial consistency in contents of generated regions and the original input.
• The second is to generate a high-quality large image with a small amount of adjacent information.