IMAGE INPAINTING USING A CONTENT PRESERVATION VALUE

Organization Name

ADOBE INC.

Inventor(s)

Yuqian Zhou of Bellevue WA (US)

Krishna Kumar Singh of San Jose CA (US)

Benjamin Delarre of San Francisco CA (US)

Zhe Lin of Clyde Hill WA (US)

Jingwan Lu of Sunnyvale CA (US)

Taesung Park of San Francisco CA (US)

Sohrab Amirghodsi of Seattle WA (US)

Elya Shechtman of Seattle WA (US)

IMAGE INPAINTING USING A CONTENT PRESERVATION VALUE

This abstract first appeared for US patent application 18454850 titled 'IMAGE INPAINTING USING A CONTENT PRESERVATION VALUE

Original Abstract Submitted

A method, non-transitory computer readable medium, apparatus, and system for image generation are described. An embodiment of the present disclosure includes obtaining an input image, an inpainting mask, and a plurality of content preservation values corresponding to different regions of the inpainting mask, and identifying a plurality of mask bands of the inpainting mask based on the plurality of content preservation values. An image generation model generates an output image based on the input image and the inpainting mask. The output image is generated in a plurality of phases. Each of the plurality of phases uses a corresponding mask band of the plurality of mask bands as an input.