Jingwan Lu

Santa Clara, CA, United States of America

Jingwan Lu

This inventor holds 102 USPTO granted patents and 13 published patent applications, primarily in Image Generation (CPC class G06T2207-20084). Top assignees: Adobe, Inc., Princeton University, Czech Technical University in Prague. Active years: 2015-2026.

USPTO Granted Patents = 102 

% Patents Active = 100.0

Average Co-Inventor Count = 5.3

ph-index = 8

Forward Citations = 213(Granted Patents)

Forward Citations (Not Self Cited) = 132(Dec 10, 2025)


Inventors with similar research interests:

🔬 See more inventors

Location History:

  • Princeton, NJ (US) (2015 - 2017)
  • San Jose, CA (US) (2019 - 2021)
  • Santa Clara, CA (US) (2017 - 2024)
  • Sunnyvale, CA (US) (2021 - 2024)

Company Filing History:


Years Active: 2015-2026

Loading Chart...
Areas of Expertise:
Image Editing
Digital Inpainting
Diffusion Models
Neural Networks
Generative Adversarial Networks
Semantic Layout
Latent Space
Cross-Attention
3D Animation
Machine Learning
Object Awareness
Real-Time Editing
102 patents (USPTO):Explore Patents

Title: Innovations by Jingwan Lu: A Pioneer in Image Generation Technologies

Introduction: Jingwan Lu, based in Santa Clara, CA, has made significant contributions to the field of image generation, holding an impressive portfolio of 65 patents. His work at leading technology companies has focused on enhancing the capabilities of generative models, leading to breakthroughs in how digital images are created and manipulated.

Latest Patents: Among Jingwan Lu's latest innovations are two notable patents that illustrate his expertise. The first is a system for user-guided image generation. This innovative system allows user input during the training process of a generative model, enabling the model to produce new images tailored to specific visual features desired by the user. So, using a fine-tuned generative model and interpretable factors, users can influence the resulting images significantly.

The second patent addresses the challenge of transferring faces between digital images. This technology utilizes latent codes combined through a blending network to generate a cohesive digital image from multiple sources. By employing a face segmentation network to create an intersection face mask, the system innovatively merges the features of the source and target images, showcasing advanced techniques in artificial intelligence.

Career Highlights: Jingwan Lu has worked at Adobe, Inc., where he focused on developing advanced image processing technologies. His role at this leading digital media company has been pivotal in bringing cutting-edge innovations to the forefront of the tech industry. His expertise in generative models positions him as a key contributor to advancements in image generation technologies.

Collaborations: During his career, Jingwan Lu has collaborated with prominent individuals in the field, including Elya Shechtman and Richard Zhang. Their collective efforts have enhanced research and development, combining their knowledge to push the boundaries of what is possible in digital image manipulation.

Conclusion: Jingwan Lu's work in the domain of image generation is profoundly influential. With his 65 patents, he demonstrates a commitment to innovation and excellence. By creating user-centric technologies that redefine how we perceive and interact with digital images, Lu continues to pioneer advancements in this dynamic field. His contributions not only enhance user experience but also set new standards for future developments in generative models.

Profile summary based on public USPTO records.
Please report any incorrect information to [email protected]
Loading…