18421082. IMAGE PROCESSING METHOD AND DEVICE FOR AI-BASED FILTERING simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
IMAGE PROCESSING METHOD AND DEVICE FOR AI-BASED FILTERING
Organization Name
Inventor(s)
Quockhanh Dinh of Suwon-si (KR)
Kwangpyo Choi of Suwon-si (KR)
IMAGE PROCESSING METHOD AND DEVICE FOR AI-BASED FILTERING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18421082 titled 'IMAGE PROCESSING METHOD AND DEVICE FOR AI-BASED FILTERING
The patent application describes an image processing method for AI-based filtering, involving obtaining motion information for inter prediction of a current block of a reconstructed image, determining reference reconstructed images, determining reference blocks using a neural network, obtaining an output block, and modifying the current reconstructed image based on the output block.
- Motion information is obtained for inter prediction of a current block.
- Reference reconstructed images are determined based on the motion information.
- Reference blocks are determined using a neural network.
- An output block corresponding to the current block is obtained.
- The current reconstructed image is modified based on the output block.
Potential Applications: - Video compression - Image enhancement - Object recognition in videos
Problems Solved: - Reduce errors between current and original blocks - Improve image quality in video processing
Benefits: - Enhanced image quality - Efficient video compression - Improved object recognition accuracy
Commercial Applications: - Video streaming services - Security surveillance systems - Medical imaging technologies
Prior Art: No prior art information provided.
Frequently Updated Research: No information on frequently updated research provided.
Questions about AI-based image processing: 1. How does the neural network improve the quality of the reconstructed image? 2. What are the potential limitations of this AI-based filtering method in image processing?
Original Abstract Submitted
An image processing method for artificial intelligence (AI)-based filtering includes: obtaining motion information regarding inter prediction of a current block of a current reconstructed image, based on the motion information regarding the inter prediction, determining at least one reference reconstructed image regarding the current reconstructed image, based on the motion information and the at least one reference reconstructed image, determining at least one reference block, by inputting the current block and the at least one reference block to a neural network, obtaining an output block corresponding to the current block, and based on the output block, obtaining a modified current reconstructed image, wherein the neural network is trained using training data including the current block, the at least one reference block, and the output block, to reduce an error between the current block and an original block corresponding to the current block.