Inventor

LU JINGWAN

US91 patents

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

LU JINGWAN

ADOBE INC

Generating modified digital images utilizing a global and spatial autoencoder

Generating neutral-pose transformations of self-portrait images

Utilizing a colorization neural network to generate colorized images based on interactive color edges

Generation of parameterized avatars

Direct regression encoder architecture and training

Attribute control techniques for image editing

Techniques for smooth region merging in image editing

Detail-preserving image editing techniques

Attribute decorrelation techniques for image editing

System and methods for modeling creation workflows

Multi-scale output techniques for generative adversarial networks

Techniques for domain to domain projection using a generative model

Facilitating sketch to painting transformations

Facilitating sketch to painting transformations

Text-based insertion and replacement in audio narration

Deep-learning-based automatic skin retouching

Generating a stylized image or stylized animation by matching semantic features via an appearance guide, a segmentation guide, and/or a temporal guide

Smart guide to capture digital images that align with a target image model

Object class inpainting in digital images utilizing class-specific inpainting neural networks

Supervised learning techniques for encoder training

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

Learning parameters for generative inpainting neural networks utilizing object-aware training and masked regularization

Generating digital images utilizing high-resolution sparse attention and semantic layout manipulation neural networks

Diverse image inpainting using contrastive learning

Generating a modified digital image utilizing a human inpainting model

Generating synthesized digital images utilizing class-specific machine-learning models

Retouching digital images utilizing separate deep-learning neural networks

Colorizing vector graphic objects

Generating composite images with objects from different times

Systems and methods of generating playful palettes from images

Real-time speaker-dependent neural vocoder

Stroke operation prediction for three-dimensional digital content

Interactive color palette interface for digital painting

Generating synthesized digital images utilizing a multi-resolution generator neural network

Capturing digital images that align with a target image model

Few-shot image generation via self-adaptation

Image generation using a text and image conditioned machine learning model

Generative image filling using a reference image

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

Iteratively modifying inpainted digital images based on changes to panoptic segmentation maps

Learning parameters for neural networks using a semantic discriminator and an object-level discriminator

Generating digital images utilizing high-resolution sparse attention and semantic layout manipulation neural networks

Enhancing detailed segments in latent code-based edited digital images

Transferring faces between digital images by combining latent codes utilizing a blending network

Digital image inpainting utilizing a cascaded modulation inpainting neural network

Retouching digital images utilizing layer specific deep-learning neural networks

ADOBE SYSTEMS INC

Illumination-guided example-based stylization of 3D renderings

Example-based edge-aware directional texture painting

Jamri{hacek over (s)}ka Ondrej

Appearance transfer techniques maintaining temporal coherence

DIVERDI STEPHEN J

Systems and methods for synthesizing high fidelity stroke data for lower dimension input strokes