Synthetic data generation for training stereo models
AssigneeNVIDIA Corporation
InventorsMatthew Trepte, Bowen Wen, Jack Zhang, Gordon Grigor, Stanley Thomas Birchfield
Life of this patent
Estimating the term…
Loading patent…
AssigneeNVIDIA Corporation
InventorsMatthew Trepte, Bowen Wen, Jack Zhang, Gordon Grigor, Stanley Thomas Birchfield
Estimating the term…
Systems and methods are disclosed that curate synthetic datasets using a stereo model. For example, embodiments of the present disclosure may include an iterative process that generates a first synthetic dataset using a replicator composer, uses the generated dataset to train a stereo model such as a Foundational Stereo model, and curates a second synthetic dataset using the trained stereo model. Additionally, and/or alternatively, the synthetic datasets that were generated by the replicator composer may include multiple categories of realism such as realistic style synthetic data and chaotic style synthetic data as well as multiple categories of use cases such as navigation, driving, and manipulation. Additionally, and/or alternatively, the replicator composer may generate a scene based on determining a center of mass of objects that are generated for the scene and using the center of mass to orient the camera.
A computer-implemented method for curating synthetic datasets using a stereo model, comprising:
A system for curating synthetic datasets using a stereo model, comprising:
A non-transitory computer-readable medium having processor-executable instructions stored thereon for curating synthetic datasets using a stereo model, wherein the processor-executable instructions, when executed, facilitate:
Dependencies are inferred from the claim text.