USPTO Patent US12586270B2: Image Editing with Generative Neural Network

The USPTO has granted patent US12586270B2 to Adobe Inc. for a method of generating and modifying digital images using a generative neural network. The patent covers systems and methods for latent-based editing of digital images by mapping feature tensors and style vectors into a joint feature style space.

USPTO Patent Grant for ML-Based AR Output Generation by Dell

The USPTO has granted Dell Products L.P. patent US12586263B2 for a machine learning-based system to generate outputs in augmented reality environments. The patent covers an apparatus that uses multiple machine learning models to process input components and generate relevant output responses for users in AR.

USPTO Patent Grant: Non-adversarial image generation using transfer learning

The USPTO has granted Adobe Inc. a patent (US12586258B2) for a method of non-adversarial image generation using transfer learning. The patent describes a system that generates latent representations and digital images based on random noise and a trained machine learning model, aiming for visual similarity to a training dataset.

Canon Patent for Information Processing Apparatus

The USPTO has granted Canon Kabushiki Kaisha a patent (US12586212B2) for an information processing apparatus and method. The patent covers a system that can perform inference and training on frames of data, with specific logic for handling cases where training is not yet complete for a frame.

USPTO Patent Grant: Analog-Digital Hybrid Computing Neuromorphic System

The USPTO has granted a patent (US12586636B2) for an analog-digital hybrid computing neuromorphic system. The patent, assigned to IHW INC., details a system utilizing non-volatile memory cells for synaptic units and a digital calculation section for processing.

USPTO Patent Grant: Neural Network Hair Modification in Digital Images

The USPTO has granted a patent (US12586157B2) to Ulta Salon, Cosmetics & Fragrance, Inc. for a method using generative neural networks to modify hair characteristics in digital images. The patent details a process for altering hair features while maintaining the original face and background.

USPTO Grants Patent for AI Feature Map Processing Method

The USPTO has granted a patent (US12586154B2) to Huawei Technologies Co., Ltd. for an AI feature map processing method and device. The patent describes a neural network model with input adaptation branches designed to downsample feature maps at different ratios.

USPTO Patent Grant: Image Processing Apparatus

The USPTO has granted a patent (US12586352B2) to CANON KABUSHIKI KAISHA for an image processing apparatus, method, and storage medium. The patent describes a system that calculates similarity between image regions and infers high-frequency components using a learning model.

USPTO Patent Grant: Digital Rights Management for Machine Learning Models

The USPTO has granted patent US12585991B2 to Deere & Company for techniques related to the digital rights management of machine learning models used in agriculture. The patent covers methods for training models to generate valid or invalid agricultural inferences based on sensor data ranges.

USPTO Grants Patent for Secure Statistical Classifier Generation

The USPTO has granted a patent (US12585988B2) to NEC Corporation of America for systems and methods for generating and applying a secure statistical classifier. The patent, filed on March 1, 2022, details a process involving cryptographic keys to create unique trained sub-classifiers.