Michael Baumer

US Patent:

20230114301, Apr 13, 2023

Filed:

Dec 7, 2022

Appl. No.:

18/076900

Inventors:

- Parkland FL, US
Seth Haberman - New York NY, US
Michael A. Baumer - Bethesda MD, US
Nakul Dawra - Miami FL, US

Assignee:

Unknot Inc. - Parkland FL

International Classification:

G06N 3/08
G06F 16/535
G06T 9/00
G06V 30/194
G06F 18/2113

Abstract:

Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.

US Patent:

20210142172, May 13, 2021

Filed:

Nov 9, 2020

Appl. No.:

17/093386

Inventors:

- Parkland FL, US
Seth Haberman - New York NY, US
Michael A. Baumer - Bethesda MD, US
Nakul Dawra - Miami FL, US

Assignee:

Unknot Inc. - Parkland FL

International Classification:

G06N 3/08
G06K 9/62
G06F 16/535

Abstract:

Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.

US Patent:

20210142525, May 13, 2021

Filed:

Nov 9, 2020

Appl. No.:

17/093359

Inventors:

- New York NY, US
Seth Haberman - New York NY, US
Michael A. Baumer - Bethesda MD, US
Nakul Dawra - Miami FL, US

Assignee:

Unknot Inc. - New York NY

International Classification:

G06T 9/00
G06K 9/66

Abstract:

Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.