Samsung patents video decoder that uses neural networks to clean up images
Samsung describes a method for decoding video where a neural network applies in-loop filtering to improve image quality. The system generates specific layer settings based on state information from reference images, which is then used to process the current frame. This approach aims to refine the visual output during the video decoding process.
In the filing’s own words
An image decoding method includes: generating, based on first state information obtained from a feature map corresponding to a first reference image for a current image or second state information obtained from a feature map corresponding to a second reference image for the current image, layer information to be used in at least one layer within a filtering neural network; inputting, to the at least one layer within the filtering neural network, information corresponding to the current image; and obtaining an image in which in-loop filtering has been applied to the current image by inputting, to the at least one layer in which the layer information has been used, the information corresponding to the current image, wherein state information for the current image is obtained from a feature map corresponding to the current image and the state information has a resolution lower than a resolution of the current image.
What exactly they claim (claim 1)
1. An image decoding method comprising: generating, based on first state information obtained from a feature map corresponding to a first reference image for a current image or second state information obtained from a feature map corresponding to a second reference image for the current image, layer information to be used in at least one layer within a filtering neural network; inputting, to the at least one layer within the filtering neural network, information corresponding to the current image; and obtaining an image in which in-loop filtering has been applied to the current image by inputting, to the at least one layer in which the layer information has been used, the information corresponding to the current image, wherein state information for the current image is obtained from a feature map corresponding to the current image and the state information for the current image has a resolution lower than a resolution of the current image.
Facts
- Company
- Samsung (SAMSUNG ELECTRONICS CO., LTD.)
- Official title
- IMAGE DECODING METHOD, IMAGE DECODING DEVICE, IMAGE ENCODING METHOD, AND IMAGE ENCODING DEVICE FOR PERFORMING IN-LOOP FILTERING BY USING NEURAL NETWORK
- Publication number
- US20260292263A1
- Application number
- 19531029
- Filed
- Feb 5, 2026
- Published
- Sep 24, 2026
- Inventors
- 2
- Claims
- 15
Classified under
H04N 19/82 Electricity & electronicsH04N 19/117 Electricity & electronicsH04N 19/136 Electricity & electronicsH04N 19/172 Electricity & electronicsH04N 19/42 Electricity & electronicsMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.