ADOBE had seven patents in metaverse during Q1 2024. ADOBE Inc has developed a system that uses neural networks to detect and segment perceptual artifacts in digital images, particularly in synthetically modified portions. The system utilizes a machine-learning model trained on labeled artifact regions to detect these artifacts and incorporates it into an iterative inpainting process for enhancing digital image quality. GlobalData’s report on ADOBE gives a 360-degree view of the company including its patenting strategy. Buy the report here.

ADOBE grant share with metaverse as a theme is 71% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Generating iterative inpainting digital images via neural network based perceptual artifact segmentations (Patent ID: US20240046429A1)

The patent filed by ADOBE Inc. discloses methods, systems, and computer-readable storage media for generating neural network-based perceptual artifact segmentations in synthetic digital image content. The system uses neural networks to detect perceptual artifacts in digital images and modifies them accordingly. It involves determining a digital image with synthetically modified portions, utilizing an artifact segmentation machine-learning model to detect perceptual artifacts in these modified portions, and employing an iterative inpainting process to inpaint digital images while detecting perceptual artifacts for additional iterations.

The computer-implemented method and system described in the patent involve utilizing machine-learning models to detect and segment perceptual artifacts in digital images, generating synthetically modified portions based on these detections, and inpainting the images accordingly. The system allows for multiple iterations of inpainting using different digital image inpainting models, selecting the best-modified portions based on artifact ratio metrics, and generating final modified digital images. The method also includes determining artifact ratios, comparing them to threshold values, and generating additional modified portions based on these comparisons. Additionally, the system can determine multiple inpainting iterations and generate final modified images based on artifact ratio metrics.

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

Premium 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

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.