Microsoft patents method to train image upscaling models using game graphics
Microsoft describes a system that creates training data for image enhancement models by generating high-resolution images and using a separate network to downscale them. This process produces paired high- and low-resolution images used to train a super-resolution model that can improve image detail or increase resolution.
In the filing’s own words
A computing system generates a trained super-resolution model using correlated high-resolution and low-resolution image pairs. A first image generator produces high-resolution images, which are processed by a downscaler network to create corresponding low-resolution images. The downscaler network is trained using an initial set of image pairs. Additional high-resolution images are generated and processed by the downscaler network to produce additional low-resolution images, forming a second set of image pairs. The super-resolution model is trained using the second set of image pairs. The trained super-resolution model processes low-resolution images to generate enhanced images with improved detail and reduced artifacts. The model can be used to increase resolution of input images or refine details without changing resolution. The trained model may be deployed on different devices and applied across various rendering environments.
What exactly they claim (claim 1)
1. A computing system comprising: at least one memory; at least one hardware processor coupled to the at least one memory; and one or more computer-readable storage media storing computer-executable instructions, that, when executed, cause the computing system to perform operations comprising: receiving a rendering package with a first image generator; in response to being provided the rendering package, using the rendering package by the first image generator to generate high-resolution images and corresponding low-resolution images; training a downscaler network with a first set of a plurality of image pairs of the high- and low-resolution images; generating additional high-resolution images with the first image generator; processing the additional high-resolution images generated by the first image generator with the downscaler network to produce additional low-resolution images; generating a second set of a plurality of image pairs from the processed additional high-resolution images and corresponding additional low-resolution images produced by the downscaler network; and training a super-resolution model using the second set of images pairs to provide a trained super-resolution model.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- GENERATION OF TRAINING DATA FOR IMPROVED SUPER-RESOLUTION MODELS OR DOWNSCALER NETWORKS
- Publication number
- US20260306944A1
- Application number
- 19171118
- Filed
- Apr 4, 2025
- Published
- Oct 8, 2026
- Inventors
- 2
- Claims
- 20
Classified under
A63F 13/52 Human necessitiesG06T 3/4046 Physics & computingG06T 3/4053 Physics & computingG06T 5/60 Physics & computingG06T 2207/20016 Physics & computingG06T 2207/20081 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 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.