18049213. MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
- 1 MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION - 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 machine learning model differentiate between the ground truth image and the synthetic image during training?
- 1.9.3 What are the specific parameters used in the optical transmission model to generate the synthetic image for training the machine learning model?
- 1.10 Original Abstract Submitted
MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION
Organization Name
Inventor(s)
Hamid R. Sheikh of Allen TX (US)
John Seokjun Lee of Allen TX (US)
MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18049213 titled 'MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION
Simplified Explanation
The method described in the patent application involves using machine learning to restore images captured by an under-display camera (UDC). Here are some key points to explain the innovation:
- Obtaining an image captured by a camera located under a display
- Processing the UDC image using a machine learning model
- Training the machine learning model using a ground truth image and a synthetic image
- Generating the synthetic image using a point spread function based on an optical transmission model of the display
- Displaying or storing the restored image corresponding to the UDC image
Potential Applications
The technology could be applied in smartphones, tablets, laptops, and other electronic devices with under-display cameras to improve image quality.
Problems Solved
This technology addresses the challenge of capturing clear and high-quality images using under-display cameras, which may be affected by display interference.
Benefits
The use of machine learning helps enhance the quality of images captured by under-display cameras, providing users with better visual experiences.
Potential Commercial Applications
- Smartphone manufacturers could integrate this technology into their devices to offer improved camera performance.
- Companies developing electronic devices with under-display cameras could license this technology to enhance their product offerings.
Possible Prior Art
One potential prior art could be the use of machine learning algorithms to enhance image quality in various applications, including photography and video processing.
Unanswered Questions
How does the machine learning model differentiate between the ground truth image and the synthetic image during training?
The machine learning model is trained using a ground truth image and a synthetic image generated using a point spread function based on an optical transmission model of the display. The model learns to differentiate between these images based on the features and patterns present in each type of image.
What are the specific parameters used in the optical transmission model to generate the synthetic image for training the machine learning model?
The synthetic image is generated using a point spread function that is based on an optical transmission model of the display. The parameters of this model may include factors such as the display's pixel density, color accuracy, and light transmission properties, which influence the final appearance of the captured image.
Original Abstract Submitted
A method includes obtaining an under-display camera (UDC) image captured using a camera located under a display. The method also includes processing, using at least one processing device of an electronic device, the UDC image based on a machine learning model to restore the UDC image. The method further includes displaying or storing the restored image corresponding to the UDC image. The machine learning model is trained using (i) a ground truth image and (ii) a synthetic image generated using the ground truth image and a point spread function that is based on an optical transmission model of the display.
