Back to results
US 2025/0029206 A1Published application
High Resolution Input Processing in a Neural Network
AssigneeNVIDIA Corporation
InventorMichael RANZINGER
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and methods to use one or more neural networks to generate information about one or more images based, at least in part, on one or more confidence scores associated with the information. In at least one embodiment, a neural network downscales an image and performs an image processing task on said downscaled image according to a query input by a user.
Claims20
A processor comprising:
- one or more circuits to use one or more neural networks to generate information about one or more images based, at least in part, on one or more confidence scores associated with the information.
A system comprising:
- one or more processors use one or more neural networks to generate information about one or more images based, at least in part, on one or more confidence scores associated with the information.
A method comprising:
- causing one or more neural networks to generate information about one or more images based, at least in part, on one or more confidence scores associated with the information.
Dependencies are inferred from the claim text.