ADOBE has been granted a patent for an image editing system that allows for object or region replacement in images. The system uses layers of masks to replace specific parts of an image with more desirable elements from another image, resulting in aesthetically pleasing composite images. The method involves generating region masks, creating a defringing layer, generating a region-specific layer, and combining multiple layers to create a composite image based on user inputs. GlobalData’s report on ADOBE gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on ADOBE, User behaviour analysis was a key innovation area identified from patents. ADOBE's grant share as of September 2023 was 75%. Grant share is based on the ratio of number of grants to total number of patents.

Image editing system for object/region replacement using masks and layers

Source: United States Patent and Trademark Office (USPTO). Credit: ADOBE Inc

A recently granted patent (Publication Number: US11776184B2) describes a method and apparatus for generating composite images using region masks and user inputs. The method involves generating region masks based on a first image using a mask generation network. These region masks include a first region mask and a second region mask, with the first region mask having a more gradual mask boundary than the second region mask.

The method further includes generating a defringing layer by combining the first region mask with a grayscale version of a second image. A region-specific layer is generated by combining the second region mask with the second image. These layers, along with the first image, are then combined to generate a composite image. The generation of the composite image is based on both local adjustments made by the user and global adjustments made by the user.

Additional features of the method include combining the second region mask with a third region mask to create a combined region mask, generating a color harmonization layer based on the region masks, and receiving user inputs through a mask brush tool. The method also allows for adjusting the position of the second image relative to the first image and automatically regenerating the composite image based on the adjusted position. The composite image can be further edited using an image editing application.

The patent also describes an apparatus that includes a mask generation network, a defringing component, a region-specific layer component, and a layer composition component. The mask generation network uses a convolutional neural network (CNN) to generate the region masks. The apparatus also includes a color harmonization component for generating a color harmonization layer based on the region masks.

Overall, this patent presents a method and apparatus for generating composite images with improved region masking and user control. The use of region masks and user inputs allows for precise adjustments and customization of the composite image.

To know more about GlobalData’s detailed insights on ADOBE, buy the report here.

Premium Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.