AI Image Coding With DNN Up-Scaling for Low-Bitrate Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image encoding and decoding technologies struggle to efficiently handle high-resolution/high-quality images, leading to increased bitrate requirements and potential information omission during compression and decompression processes.
Innovation Solution
An AI-based encoding and decoding method and apparatus that utilize deep neural networks (DNNs) for down-scaling and up-scaling images, allowing for different resolution ratios in horizontal and vertical directions, thereby reducing bitrate and preventing information omission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional image encoding is used for high-resolution images, then image quality is maintained, but bitrate increases significantly
Solution Approach 1:
The patent segments the image encoding process into two stages: first down-scaling the high-resolution image to a lower resolution representation, then encoding that compressed version. This segmentation allows the system to handle high-resolution images without encoding all detail at full resolution, thereby reducing bitrate while maintaining acceptable quality through the subsequent up-scaling process.
Solution Approach 2:
The patent introduces an intermediary representation - a down-scaled version of the image that serves as a bridge between the original high-resolution image and the final encoded output. This intermediary low-resolution representation is what gets encoded and transmitted, allowing quality preservation without the full bitrate cost of encoding the original high-resolution image directly.
2Quantity of substance
If image down-scaling is applied to reduce resolution, then bitrate is reduced, but information is lost
Solution Approach 1:
The patent applies preliminary action by down-scaling the image before encoding. The high-resolution image is first converted to a lower-resolution version, which is then encoded at reduced bitrate. The encoded data is subsequently used to reconstruct the image at the desired resolution, effectively preparing the image for efficient compression while preserving the ability to recover detailed information.
Solution Approach 2:
The patent changes the resolution parameter of the image by applying down-scaling transformation. This parameter change allows the same image content to be represented with fewer bits during encoding, and the system compensates for the resolution reduction through up-scaling during decoding, thereby changing the representation parameters to optimize bitrate efficiency.
3Device complexity
If conventional encoding is used, then encoding process is simple, but information omission occurs during compression and decompression
Solution Approach 1:
The patent ensures continuity of useful action by implementing a complete cycle of down-scaling, encoding, and up-scaling operations. The down-scaling process is followed by encoding, and then the encoded data is used for up-scaling reconstruction. This continuous process ensures that information is not lost but rather transformed through different resolution representations, maintaining data integrity throughout the compression-decompression cycle.
Data Source
AI summary
An AI decoding apparatus includes a memory storing instructions and a processor configured to execute the instructions to obtain AI data related to AI down-scaling of an original image and image data generated as a result of encoding a first image, obtain a second image corresponding to the first image by decoding the image data, determine a resolution ratio in a horizontal direction and a resolution ratio in a vertical direction between the original image and the first image, based on the AI data, and obtain, by an up-scaling deep neural network (DNN), a third image in which a resolution in at least one of a horizontal direction and a vertical direction is increased from the second image based on the resolution ratio in the horizontal direction and the resolution ratio in the vertical direction.