Vancouver, Canada

Karsten Julian Kreis

This inventor holds 18 USPTO granted patents and 36 published patent applications, primarily in Generative Modeling. Top assignee: Nvidia Corporation. Active years: 2022-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Karsten Julian Kreis. Retrieved from https://idiyas.com/inventor/karsten-julian-kreis

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

USPTO Granted Patents = 18 

% Patents Active = 100.0

Average Co-Inventor Count = 5.0

ph-index = 2

Forward Citations = 17(Granted Patents)


Location History:

  • Vancouver, CA (2023)
  • Vancover, CA (2022 - 2024)

Company Filing History:


Years Active: 2022-2026

Loading Chart...
Areas of Expertise:
Image Diffusion Models
3D Scene Geometries
Neural Implicit Representations
Variational Autoencoders
Content Generation
Denoising GANs
Voxel Representations
Latent Diffusion Models
Semantic Image Editing
Differential Privacy
Real-Time Rendering
Synthetic Data Generation
18 patents (USPTO):Explore Patents

Title: The Innovative Mind of Karsten Julian Kreis

Introduction

Karsten Julian Kreis is a prominent inventor based in Vancouver, Canada. He has made significant contributions to the field of technology, particularly in the area of three-dimensional shape synthesis and generative models. With a total of 18 patents to his name, Kreis continues to push the boundaries of innovation.

Latest Patents

Kreis's latest patents include groundbreaking work on synthesizing three-dimensional shapes using latent diffusion models in content generation systems and applications. The approaches presented in this patent provide for the unconditional generation of novel three-dimensional object shape representations, such as point clouds or meshes. In one embodiment, a first denoising diffusion model (DDM) is trained to synthesize a 1D shape latent from Gaussian noise, while a second DDM generates a set of latent points conditioned on this 1D shape latent. This innovative method allows for the generation of a 3D point cloud representative of random objects from the classes on which the models were trained. Additionally, Kreis has developed a patent on denoising diffusion generative adversarial networks. This technology reduces the number of denoising steps during a reverse process, enabling faster sample generation from noise.

Career Highlights

Kreis is currently employed at Nvidia Corporation, where he applies his expertise in advanced technologies. His work at Nvidia has positioned him as a leader in the field of generative models and artificial intelligence.

Collaborations

Throughout his career, Kreis has collaborated with notable professionals in the industry, including Sanja Fidler and Arash Vahdat. These collaborations have further enhanced his innovative capabilities and contributions to technology.

Conclusion

Karsten Julian Kreis exemplifies the spirit of innovation through his groundbreaking patents and contributions to the field of technology. His work continues to inspire advancements in three-dimensional shape synthesis and generative models.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…