Robust training of large-scale object detectors with a noisy dataset

Z Lin, M Ling, J Zhang, J Kuen, F Perazzi… - US Patent …, 2021 - Google Patents
Abstract Systems and methods are described for object detection within a digital image
using a hierarchical softmax function. The method may include applying a first softmax …

Denoising Monte Carlo renderings using machine learning with importance sampling

T Vogels, F Rousselle, B McWilliams, M Meyer… - US Patent …, 2020 - Google Patents
Supervised machine learning using neural networks is applied to denoising images
rendered by MC path tracing. Specialization of neural networks may be achieved by using a …

Temporal techniques of denoising Monte Carlo renderings using neural networks

T Vogels, F Rousselle, J Novak, B McWilliams… - US Patent …, 2022 - Google Patents
A modular architecture is provided for denoising Monte Carlo renderings using neural
networks. The temporal approach extracts and combines feature representations from …

Method of and server for training a machine learning algorithm for estimating uncertainty of a sequence of models

GG MELANÇON, W Gharbieh, I Malik… - US Patent …, 2023 - Google Patents
2020-10-01 Assigned to ELEMENT AI INC. reassignment ELEMENT AI INC. ASSIGNMENT
OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: MALIK, IMAN …

Training image signal processors using intermediate loss functions

A Sutic, Z Zivkovic, G Michael - US Patent 10,796,200, 2020 - Google Patents
In an example method for training image signal processors, a reconstructed image is
generated via an image signal processor based on a sensor image. An intermediate loss …

Denoising Monte Carlo renderings using progressive neural networks

T Vogels, F Rousselle, B McWilliams, M Meyer… - US Patent …, 2021 - Google Patents
Supervised machine learning using neural networks is applied to denoising images
rendered by MC path tracing. Specialization of neural networks may be achieved by using a …

Systems and methods for optimized computer vision using deep neural networks and Litpschitz analysis

R Balan, MK Singh, D Zou - US Patent 10,839,253, 2020 - Google Patents
Computer vision systems and methods for optimized computer vision using deep neural
networks and Lipschitz analysis are provided. The system receives signals or data related to …

Large-scale generation of photorealistic 3d models

G Elbaz - US Patent App. 17/791,455, 2023 - Google Patents
Starting with a small dataset of 3D base models, each model including 3D mesh and texture
feature map definitions, procedural modifications of the 3D meshes and the texture feature …

Fastestimator healthcare ai framework

X Dong, A Chowdhury, J Hong, HM Chang… - US Patent App. 16 …, 2020 - Google Patents
An artificial intelligence platform and associated methods of training and use are disclosed.
An example apparatus includes a data pipeline to: preprocess data using one or more …

Systems and methods for deep-learning based super-resolution using multiple degradations on-demand learning

SNRD Reddy, Q Dai - US Patent 11,521,131, 2022 - Google Patents
(57) ABSTRACT A machine learning model can be trained using a first set of degraded
images for each of a plurality of combinations and corresponding reference images, where a …