Microsoft patents step-by-step training for clearer image upscaling
This patent describes a method for training AI models that enlarge low-resolution images into high-resolution ones. The process happens in stages, starting with basic math checks and moving to more complex visual quality checks before final adjustments.
In the filing’s own words
Phased loss function training of machine learning models that are configured for performing super-resolution image processing includes training with two or more discrete phases that each apply different combinations of loss function training to the super-resolution models. In a first phase, for example, a first loss function is applied to the model that is a per-pixel or a non-perceptual loss function. In a second phase, which begins after the model reaches a threshold of convergence in the first phase, a blended loss function is applied, which includes the application of at least one perceptual loss function. Then, after the model reaches a subsequent threshold of convergence in the second phase, which is greater than the threshold of convergence in the first phase, the model is optionally further modified with optimizations such as quantization and/or sparsity optimizations for further facilitating subsequent super-resolution processing.
What exactly they claim (claim 1)
1. A method for performing multi-phase loss function training of a super-resolution model, the method comprising: accessing a super-resolution model configured with algorithms having modifiable weights, the algorithms taking input variables associated with low-resolution image data and generating output comprising high-resolution image data; training the super-resolution model with a first loss function of a first loss function type in a first training phase; subsequent to the first training phase, in a second training phase, training the super-resolution model with a second loss function of a second loss function type that is not used during the first training phase; and subsequent to the second training phase, optimizing the super-resolution model by using at least one of a quantization optimization or a sparsity optimization.
Facts
- Company
- Microsoft (MICROSOFT TECHNOLOGY LICENSING, LLC)
- Official title
- Phased loss function training for super-resolution models
- Patent number
- US12731213B2
- Application number
- 18325727
- Filed
- May 30, 2023
- Granted
- Sep 8, 2026
- Inventors
- 3
- Claims
- 16
Classified under
G06T 3/4053 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.