View source for Samsung electronics co., ltd. (20240135673). MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION simplified abstract

=MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION=


==Organization Name==

[[:Category:samsung electronics co., ltd.|samsung electronics co., ltd.]]


[[Category:samsung electronics co., ltd.]]

==Inventor(s)==

[[:Category:Yibo Xu of Plano TX (US)|Yibo Xu of Plano TX (US)]][[Category:Yibo Xu of Plano TX (US)]]

[[:Category:Weidi Liu of Houston TX (US)|Weidi Liu of Houston TX (US)]][[Category:Weidi Liu of Houston TX (US)]]

[[:Category:Hamid R. Sheikh of Allen TX (US)|Hamid R. Sheikh of Allen TX (US)]][[Category:Hamid R. Sheikh of Allen TX (US)]]

[[:Category:John Seokjun Lee of Allen TX (US)|John Seokjun Lee of Allen TX (US)]][[Category: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 20240135673 titled 'MACHINE LEARNING MODEL TRAINING USING SYNTHETIC DATA FOR UNDER-DISPLAY CAMERA (UDC) IMAGE RESTORATION

==Simplified Explanation==

The patent application describes a method for processing images captured by an under-display camera using machine learning to enhance the image quality.

* The method involves obtaining an image captured by an under-display camera, processing the image using a machine learning model to restore it, and displaying or storing the restored image.
* The machine learning model is trained using a ground truth image and a synthetic image generated based on an optical transmission model of the display.
* The innovation aims to improve the image quality captured by under-display cameras by utilizing machine learning algorithms for image restoration.

== Potential Applications ==
The technology can be applied in smartphones, tablets, laptops, and other electronic devices with under-display cameras to enhance the quality of images captured by these cameras.

== Problems Solved ==
This technology addresses the challenge of image quality degradation in under-display cameras by using machine learning algorithms to restore and enhance the captured images.

== Benefits ==
The benefits of this technology include improved image quality, enhanced user experience, and better performance of under-display cameras in electronic devices.

== Potential Commercial Applications ==
The technology can be utilized in the consumer electronics industry for the development of devices with under-display cameras that offer superior image quality and user experience.

== Possible Prior Art ==
One possible prior art could be the use of machine learning algorithms for image enhancement in digital cameras or smartphones.

=== Unanswered Questions ===

=== How does this technology compare to existing image processing methods for under-display cameras? ===
This article does not provide a direct comparison with existing image processing methods for under-display cameras. It would be helpful to understand the specific advantages and limitations of this technology compared to traditional image processing techniques.

=== What are the potential limitations or challenges of implementing this technology in commercial devices? ===
The article does not address the potential limitations or challenges of implementing this technology in commercial devices. It would be important to consider factors such as cost, compatibility, and scalability when integrating this technology into electronic devices for mass production.


==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.



[[Category:G06V10/70]]
[[Category:G06T5/00]]
[[Category:G06V10/60]]