Active
Standard
Most Recent
IEEE 1857.11:2024
IEEE Draft Standard for Neural Network-Based Image Coding
Summary
New IEEE Standard - Active - Draft.
This standard defines a set of tools for efficient image coding, including tools for encoding, for decoding, and for encapsulation. Some of the tools are based on trained neural networks, and shall perform block partitioning, prediction, transform, quantization, entropy coding, filtering, etc., respectively.
This standard defines a set of tools for efficient image coding, including tools for encoding, for decoding, and for encapsulation. All or some of the tools may be based on trained neural networks, and may perform block partitioning, prediction, transform, quantization, entropy coding, filtering, etc.
This standard provides efficient, neural network-based coding tools for compression, decompression, and packaging of image data, which significantly improve the compression efficiency compared to IEEE Std 1857.4 (intrapicture coding) and IEEE Std 1857.10 (intrapicture coding) under comparable settings, and facilitate the compression and decompression on top of neural network-oriented computing infrastructures like neural network processing units (NPUs). The target applications and services include but are not limited to Internet images, user-generated images, and other image-enabled applications and services such as digital image storage and communications.
This standard defines a set of tools for efficient image coding, including tools for encoding, for decoding, and for encapsulation. Some of the tools are based on trained neural networks, and shall perform block partitioning, prediction, transform, quantization, entropy coding, filtering, etc., respectively.
This standard defines a set of tools for efficient image coding, including tools for encoding, for decoding, and for encapsulation. All or some of the tools may be based on trained neural networks, and may perform block partitioning, prediction, transform, quantization, entropy coding, filtering, etc.
This standard provides efficient, neural network-based coding tools for compression, decompression, and packaging of image data, which significantly improve the compression efficiency compared to IEEE Std 1857.4 (intrapicture coding) and IEEE Std 1857.10 (intrapicture coding) under comparable settings, and facilitate the compression and decompression on top of neural network-oriented computing infrastructures like neural network processing units (NPUs). The target applications and services include but are not limited to Internet images, user-generated images, and other image-enabled applications and services such as digital image storage and communications.
Notes
Active
Technical characteristics
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| Publication Date | 12/20/2024 |
| Page Count | 159 |
| EAN | --- |
| ISBN | --- |
| Weight (in grams) | --- |
| Brochures |
|
Amendments replaces
Previous versions
20/12/2024
Active
Most Recent
