Inventor

YANG JIMEI

US61 patents

⚠️ This page may combine multiple inventors who share the name “YANG JIMEI”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

YANG JIMEI

ADOBE INC

Deep salient content neural networks for efficient digital object segmentation

Digital image completion using deep learning

Instance-level semantic segmentation system

Hierarchical scale matching and patch estimation for image style transfer with arbitrary resolution

Inserting three-dimensional objects into digital images with consistent lighting via global and local lighting information

Digital image completion by learning generation and patch matching jointly

Transferring motion between consecutive frames to a digital image

Automatically segmenting images based on natural language phrases

Utilizing deep learning for boundary-aware image segmentation

Retargeting skeleton motion sequences through cycle consistency adversarial training of a motion synthesis neural network with a forward kinematics layer

Editing digital images utilizing a neural network with an in-network rendering layer

Guided up-sampling for image inpainting

Human inpainting utilizing a segmentation branch for generating an infill segmentation map

Generating a modified digital image utilizing a human inpainting model

Iterative image inpainting with confidence feedback

Digital image completion by learning generation and patch matching jointly

Digital image completion using deep learning

Foreground-aware image inpainting

User-guided image completion with image completion neural networks

Predicting patch displacement maps using a neural network

Deep high-resolution style synthesis

Multi-style texture synthesis

Contact-aware retargeting of motion

Motion retargeting with kinematic constraints

Forecasting multiple poses based on a graphical image

Motion retargeting with kinematic constraints

3D motion effect from a 2D image

Line drawing generation

Sketch-based 3D fluid volume generation using a machine learning system

Identifying and providing digital images depicting human poses utilizing visual interactive content search and virtual mannequins

Motion model refinement based on contact analysis and optimization

Generating novel views of a three-dimensional object based on a single two-dimensional image

Utilizing a warped digital image with a reposing model to synthesize a modified digital image

Iterative image inpainting with confidence feedback

Predicting patch displacement maps using a neural network

Foreground-aware image inpainting

Hierarchical scale matching and patch estimation for image style transfer with arbitrary resolution

Digital image layout training using wireframe rendering within a generative adversarial network (GAN) system

Generating realistic animations for digital animation characters utilizing a generative adversarial network and a hip motion prediction network

Transferring image style to content of a digital image

Inserting three-dimensional objects into digital images with consistent lighting via global and local lighting information

Systems and methods for mesh generation

Oil painting stroke simulation using neural network

Motion model refinement based on contact analysis and optimization

ADOBE SYSTEMS INC

Forecasting multiple poses based on a graphical image

Utilizing deep learning for boundary-aware image segmentation

Automatically segmenting images based on natural language phrases

Image object segmentation using examples

Labeling objects in image scenes

Recognizing combinations of body shape, pose, and clothing in three-dimensional input images