Generating virtual sensor parameters using large language models for synthetic data generation
AssigneeNVIDIA Corporation
InventorMario Viviani
Life of this patent
Estimating the term…
Abstract
Approaches presented herein provide systems and methods for generating one or more parameters for a content generation environment. One or more trained models may be used to generate parameters for the content generation environment based on a provided input. The input may be evaluated and then parsed or otherwise formatted to generate a deterministic output from the one or more trained models. A modified input generated from the input may then be provided to the one or more models for generation of the requested parameters. A configuration file may be generated and/or the parameters may be directly provided to an environment to configure different components based on the generated parameters.
Claims6
A computer-implemented method, comprising:
- determining, from a natural language input and an image input, an input format for a request for a set of sensor parameters;
- identifying, from the natural language input and the image input, one or more features associated with the input format;
- generating a request input, based at least on the natural language input, the image input, and the input format;
- selecting, based on the input format, a template associated with the request input;
- populating the template using at least some of the one or more features;
- providing the request input to a trained language model to generate the set of sensor parameters according to an output format associated with the request;
- receiving, from the trained language model, the set of sensor parameters;
- providing the set of sensor parameters, in the output format, to an interaction environment;
- and
- causing the interaction environment to initialize one or more objects based, at least, on the set of sensor parameters.
Dependencies are inferred from the claim text.