18053111. RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS simplified abstract (ADOBE INC.)
Contents
- 1 RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.9.1 Unanswered Questions
- 1.9.2 How does the system handle noise or artifacts in the digital image that may affect the accuracy of the neural network predictions?
- 1.9.3 What is the computational overhead of embedding a neural network within a digital image, and how does it impact the overall performance of the system?
- 1.10 Original Abstract Submitted
RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS
Organization Name
Inventor(s)
Michael S. Brown of Toronto (CA)
Brian Price of San Jose CA (US)
Scott Cohen of Sunnyvale CA (US)
RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18053111 titled 'RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS
Simplified Explanation
The patent application describes a system that embeds a trained neural network within a digital image to enhance color accuracy and expand the gamut of the image.
- The system identifies out-of-gamut pixel values in a digital image and determines target pixel values in a larger gamut that correspond to these out-of-gamut values.
- A neural network is trained to predict the target pixel values based on the out-of-gamut values.
- The trained neural network is embedded within the digital image to allow for extraction and restoration of the image to a larger gamut.
Potential Applications
This technology could be applied in various industries such as photography, graphic design, and printing to enhance color accuracy and gamut expansion in digital images.
Problems Solved
This technology addresses the issue of color accuracy and gamut limitations in digital images by using a trained neural network to predict target pixel values in a larger gamut.
Benefits
The benefits of this technology include improved color accuracy, expanded gamut range, and enhanced image quality in digital images.
Potential Commercial Applications
One potential commercial application of this technology could be in the printing industry, where accurate color reproduction is essential for high-quality prints.
Possible Prior Art
One possible prior art for this technology could be existing methods of color correction and gamut expansion in digital images, but the use of a trained neural network embedded within the image is a novel approach to address these issues.
Unanswered Questions
How does the system handle noise or artifacts in the digital image that may affect the accuracy of the neural network predictions?
The system may need to include algorithms or filters to preprocess the image data and reduce noise before training the neural network to ensure accurate predictions.
What is the computational overhead of embedding a neural network within a digital image, and how does it impact the overall performance of the system?
The system may need to optimize the size and complexity of the neural network to minimize computational overhead while still achieving accurate predictions.
Original Abstract Submitted
Systems, methods, and non-transitory computer-readable media embed a trained neural network within a digital image. For instance, in one or more embodiments, the systems identify out-of-gamut pixel values of a digital image in a first gamut, where the digital image is converted to the first gamut from a second gamut. Furthermore, the systems determine target pixel values of a target version of the digital image in the first gamut that correspond to the out-of-gamut pixel values. The systems train a neural network to predict the target pixel values in the first gamut based on the out-of-gamut pixel values. The systems embed the neural network within the digital image in the second gamut to allow for extraction of the embedded neural network from the digital image to restore the digital image to a larger gamut digital image.
