Samsung electronics co., ltd. (20240095883). IMAGE PROCESSING DEVICE, ELECTRONIC DEVICE HAVING THE SAME, AND OPERATING METHOD THEREOF simplified abstract
IMAGE PROCESSING DEVICE, ELECTRONIC DEVICE HAVING THE SAME, AND OPERATING METHOD THEREOF
Organization Name
Inventor(s)
Seungwon Choi of Suwon-si (KR)
Jongseong Choi of Suwon-si (KR)
IMAGE PROCESSING DEVICE, ELECTRONIC DEVICE HAVING THE SAME, AND OPERATING METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240095883 titled 'IMAGE PROCESSING DEVICE, ELECTRONIC DEVICE HAVING THE SAME, AND OPERATING METHOD THEREOF
Simplified Explanation
The method described in the abstract involves using neural networks to denoise frames in a video sequence. Here is a simplified explanation of the abstract:
- Acquiring a current frame, a noise dispersion map, and a first denoised frame for a previous frame.
- Generating a weighted first denoised frame based on the noise dispersion map, the current frame, and the first denoised frame using a first neural network.
- Generating an initial fused image based on the current frame and the weighted first denoised frame using a second neural network.
- Generating a second denoised frame for the current frame based on the initial fused image using a third neural network.
- Potential Applications
This technology could be applied in video processing, surveillance systems, and image enhancement applications.
- Problems Solved
This technology helps in reducing noise in video frames, improving image quality, and enhancing visual content.
- Benefits
The benefits of this technology include improved video quality, enhanced image clarity, and better visual content for various applications.
- Potential Commercial Applications
Potential commercial applications of this technology include video editing software, security systems, and digital image processing tools.
- Possible Prior Art
One possible prior art for this technology could be existing denoising algorithms used in image and video processing software.
- Unanswered Questions
- How does this method compare to traditional denoising techniques?
This article does not provide a direct comparison between this method and traditional denoising techniques. It would be helpful to understand the specific advantages or limitations of this approach compared to more conventional methods.
- What is the computational cost of implementing this method?
The abstract does not mention the computational resources required to implement this method. Understanding the computational cost could be crucial for assessing the feasibility of using this technology in real-time applications.
Original Abstract Submitted
a method includes acquiring a current frame, a noise dispersion map for the current frame, and a first denoised frame for a previous frame; generating a weighted first denoised frame based on the noise dispersion map, the current frame, and the first denoised frame using a first neural network; generating an initial fused image based on the current frame and the weighted first denoised frame using a second neural network; and generating a second denoised frame for the current frame based on the initial fused image using a third neural network.
