Huawei technologies co., ltd. (20240105193). Feature Data Encoding and Decoding Method and Apparatus simplified abstract

Feature Data Encoding and Decoding Method and Apparatus

Organization Name

huawei technologies co., ltd.

Inventor(s)

Jue Mao of Hangzhou (CN)

Yin Zhao of Hangzhou (CN)

Ning Yan of Shenzhen (CN)

Haitao Yang of Shenzhen (CN)

Lian Zhang of Shenzhen (CN)

Jing Wang of Beijing (CN)

Yibo Shi of Beijing (CN)

Feature Data Encoding and Decoding Method and Apparatus - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240105193 titled 'Feature Data Encoding and Decoding Method and Apparatus

Simplified Explanation

The patent application describes methods and apparatuses for picture or audio encoding and decoding using artificial intelligence-based technologies, specifically neural network-based encoding and decoding of picture or audio feature variables. The encoding method involves obtaining a target with multiple feature elements, determining whether to perform entropy encoding on a specific feature element based on probability estimation results, and performing entropy encoding only when necessary.

• Simplified Explanation:

  - Picture or audio encoding and decoding using AI-based neural networks.
  - Determine if entropy encoding is needed for specific feature elements.
  - Perform entropy encoding only when necessary.

1. 1. 1. Potential Applications:

- Image or audio compression for efficient storage and transmission. - Enhancing image or audio quality in multimedia applications.

1. 1. 1. Problems Solved:

- Efficient encoding and decoding of picture or audio data. - Improved compression techniques for multimedia files.

1. 1. 1. Benefits:

- Reduced file sizes without compromising quality. - Faster data transmission and processing. - Enhanced user experience in multimedia applications.

1. 1. 1. Potential Commercial Applications:
         1. AI-Based Picture or Audio Encoding and Decoding for Multimedia Industries

1. 1. 1. Possible Prior Art:

- Existing image or audio compression algorithms. - Traditional entropy encoding techniques.

1. 1. 1. 1. Unanswered Questions:
         2. How does this technology compare to existing compression methods?

- Answer: This technology offers improved efficiency and quality compared to traditional compression techniques.

1. 1. 1. 1. What impact could this have on the multimedia industry?

- Answer: This technology could revolutionize multimedia applications by enabling faster data processing and enhanced user experiences.

Original Abstract Submitted

this application provides picture or audio encoding and decoding methods and apparatuses, and relates to the field of artificial intelligence (ai)—based picture or audio encoding and decoding technologies, and specifically, to the field of neural network-based picture feature map or audio feature variable encoding and decoding technologies. the encoding method includes: obtaining a to-be-encoded target, where the to-be-encoded target includes a plurality of feature elements, and the plurality of feature elements include a first feature element. the method further includes: obtaining a probability estimation result of the first feature element; determining, based on the probability estimation result of the first feature element, whether to perform entropy encoding on the first feature element; and performing entropy encoding on the first feature element only when it is determined that entropy encoding needs to be performed on the first feature element.