ADOBE had 17 patents in future of work during Q2 2024. ADOBE Inc’s patents in Q2 2024 focus on digital content stylization using a neural photofinisher, a consolidated graphical user interface for workflow journey visualization, and conflict resolution in collaborative digital content editing. The stylization technique involves training a neural network to transfer styles from reference digital content to generate stylized images automatically. The graphical user interface visually represents a user profile’s state within a workflow journey, while the conflict resolution system handles editing operations on digital objects in collaborative environments. GlobalData’s report on ADOBE gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
ADOBE had no grants in future of work as a theme in Q2 2024.
Recent Patents
Application: Neural photofinisher digital content stylization (Patent ID: US20240202989A1)
The patent filed by ADOBE Inc. describes digital content stylization techniques that utilize a neural photofinisher to create stylized digital images. The system involves training a neural network to perform style transfer operations using reference digital content with a specific visual style, calculating style loss, generating feature maps of scenes depicted in digital images, determining visual parameter values based on the feature map and style loss, and automatically applying these values to create stylized digital images without user intervention. The system can handle various visual styles, including those from digital videos, and incorporates image statistics and visual attributes like temperature, tint, exposure, contrast, and saturation.
Additionally, the patent outlines a method involving training neural proxies of a differentiable neural photofinisher to perform photofinishing operations using tapout training data, receiving input data with digital images and parameter values defining visual attributes, and generating stylized digital images through order-independent transformations by the neural proxies. These transformations model various image processing operations, such as saturation, vibrance, RGB toning, tone mapping, texture, color conversion, gamma correction, and demosaicing, to achieve specific visual effects. The method also includes generating perturbations to manipulate image classifiers and predicting visual parameter values based on edited digital images processed by a reference photofinishing pipeline, such as an image signal processing pipeline of a mobile device camera, using a neural photofinisher implementing first-order gradient descent.
To know more about GlobalData’s detailed insights on ADOBE, buy the report here.
Data Insights
From
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.
