18372409. ARTIFICIAL INTELLIGENCE-BASED IMAGE ENCODING AND DECODING APPARATUS, AND IMAGE ENCODING AND DECODING METHOD THEREBY simplified abstract (Samsung Electronics Co., Ltd.)
Contents
- 1 ARTIFICIAL INTELLIGENCE-BASED IMAGE ENCODING AND DECODING APPARATUS, AND IMAGE ENCODING AND DECODING METHOD THEREBY
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ARTIFICIAL INTELLIGENCE-BASED IMAGE ENCODING AND DECODING APPARATUS, AND IMAGE ENCODING AND DECODING METHOD THEREBY - 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
- 1.10 Original Abstract Submitted
ARTIFICIAL INTELLIGENCE-BASED IMAGE ENCODING AND DECODING APPARATUS, AND IMAGE ENCODING AND DECODING METHOD THEREBY
Organization Name
Inventor(s)
Quockhanh Dinh of Suwon-si (KR)
Kwangpyo Choi of Suwon-si (KR)
ARTIFICIAL INTELLIGENCE-BASED IMAGE ENCODING AND DECODING APPARATUS, AND IMAGE ENCODING AND DECODING METHOD THEREBY - A simplified explanation of the abstract
This abstract first appeared for US patent application 18372409 titled 'ARTIFICIAL INTELLIGENCE-BASED IMAGE ENCODING AND DECODING APPARATUS, AND IMAGE ENCODING AND DECODING METHOD THEREBY
Simplified Explanation
The abstract describes an AI-based image decoding method where a transform block is obtained from a bitstream, a transform kernel is generated using a neural network, a residual block is obtained by applying the transform kernel to the transform block, and the current block is reconstructed using the residual block and a prediction block.
- Transform block obtained from bitstream
- Transform kernel generated using neural network
- Residual block obtained by applying transform kernel
- Current block reconstructed using residual block and prediction block
Potential Applications
The technology can be applied in various fields such as image and video compression, medical imaging, surveillance systems, and autonomous vehicles.
Problems Solved
1. Efficient image decoding process 2. Improved image quality and accuracy 3. Reduction in data storage requirements
Benefits
1. Faster image decoding 2. Enhanced image quality 3. Reduced storage space needed for image data
Potential Commercial Applications
Optimized Image Decoding Technology for Enhanced Visual Quality
Possible Prior Art
One possible prior art could be traditional image decoding methods that do not utilize AI for generating transform kernels and predicting blocks.
Unanswered Questions
How does the neural network learn to generate the transform kernel?
The abstract does not provide details on the training process of the neural network to generate the transform kernel. This information would be crucial in understanding the efficiency and accuracy of the image decoding method.
What coding context information is used in generating the transform kernel?
The abstract mentions the use of coding context information in generating the transform kernel, but it does not specify what type of information is considered. Understanding the specific parameters involved in this process would provide insights into the performance of the AI-based image decoding method.
Original Abstract Submitted
An artificial intelligence (AI)-based image decoding method and an apparatus performing the AI-based image decoding method are provided. According to the AI-based image decoding method, a transform block for a residual block of a current block is obtained from a bitstream, a transform kernel for the transform block is generated by applying, to a neural network, a prediction block for the current block, neighboring pixels of the current block, and coding context information, the residual block is obtained by applying the generated transform kernel to the transform block, and the current block is reconstructed by using the residual block and the prediction block.