Google patents method to speed up 3D model training from photos
This patent describes a technique for training neural radiance fields, which are computer models that create 3D scenes from 2D photos. It uses a mathematical step called preconditioning to adjust camera settings, helping the computer learn the 3D structure faster and more accurately.
In the filing’s own words
Systems and methods for training a machine-learned model are disclosed herein. The method can include obtaining, by a processor, a plurality of images, each image having a set of parameter values comprising values for a plurality of camera parameters and determining a covariance matrix for the plurality of camera parameters with respect to a plurality of projected points generated via evaluation of a projection function. The method can also include performing a whitening algorithm to identify a preconditioning matrix that, when applied to the sets of parameter values, results in the covariance matrix being approximately equal to an identity matrix and performing an optimization algorithm on the plurality of sets of parameter values, Performing the optimization algorithm can include applying an inverse of the preconditioning matrix to the plurality of sets of parameters in a forward prediction pass and applying the preconditioning matrix in a backward gradient pass.
What exactly they claim (claim 1)
1. A computer-implemented method for training a machine-learned model, the method comprising: obtaining, by a processor, a plurality of images, wherein a plurality of sets of parameter values are respectively associated with the plurality of images, each set of parameter values comprising values for a plurality of camera parameters; determining, by the processor, a covariance matrix for the plurality of camera parameters with respect to a plurality of projected points generated via evaluation of a projection function at the plurality of sets of parameter values; performing, by the processor, a whitening algorithm to identify a preconditioning matrix that, when applied to the plurality of sets of parameter values, results in the covariance matrix being approximately equal to an identity matrix; and performing, by the processor, an optimization algorithm on the plurality of sets of parameter values, wherein performing the optimization algorithm comprises: applying an inverse of the preconditioning matrix to the plurality of sets of parameters in a forward prediction pass; and applying the preconditioning matrix in a backward gradient pass.
Facts
- Company
- Google (Google LLC)
- Official title
- Camera parameter preconditioning for neural radiance fields
- Patent number
- US12762643B2
- Application number
- 18502736
- Filed
- Nov 6, 2023
- Granted
- Oct 13, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06T 3/06 Physics & computingG06T 7/97 Physics & computingG06T 2207/20081 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.