Microsoft patents AI method for turning 2D photos into 3D product images
Microsoft has patented a system that uses AI to turn a standard 2D photo or video of a specific product into a 3D image. The software isolates the object from the background, teaches the AI model to recognize that specific item, and then generates a new 3D view that keeps the product's original look.
In the filing’s own words
A data processing system includes: a processor; a memory storing executable instructions which, when executed by the processor, cause the processor, alone or in combination with other processors, to implement a client application with a user interface. The client application is configured to: receive an image depicting an object; generate a fine-tuning input to an image-generating Artificial Intelligence (AI) model to associate image data of the object with an identifier; with the fine-tuning input, fine-tune the AI model; structure a prompt for the AI model using the identifier; and obtain from the AI model a new customized image that depicts the object while preserving an appearance of the object.
What exactly they claim (claim 1)
1. A data processing system comprising; a processor; a memory storing executable instructions which, when executed by the processor, cause the processor, alone or in combination with other processors, to implement a client application with a user interface to: receive a two-dimensional image or a video depicting a desired object and a textual name of the desired object among other objects, wherein the desired object in combination with the textual name is a product having a specific appearance; provide the two-dimensional image or the video to an instance segmentation model to produce object image data of only the desired object from the two-dimensional image or the video based in part on the textual name of the desired object; generate a fine-tuning input to an image-generating Artificial Intelligence (AI) model to associate the object image data with a rare text identifier; with the fine-tuning input, fine-tune the AI model; structure a prompt for the AI model using the rare text identifier; and obtain from the AI model a customized three-dimensional (3D) image that depicts the desired object while preserving the specific appearance of the product.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Method and system of generating customized three-dimensional images
- Patent number
- US12737971B2
- Application number
- 18319536
- Filed
- May 18, 2023
- Granted
- Sep 15, 2026
- Inventors
- 9
- Claims
- 15
Classified under
G06T 17/00 Physics & computingG06T 7/174 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.