Beijing, China

Yikai Wang

This inventor holds 8 USPTO granted patents and 6 published patent applications and 1 EPO patent. Top assignees: Intel Corporation, Futureverse IP Limited. Active years: 2024-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Yikai Wang. Retrieved from https://idiyas.com/inventor/yikai-wang-6gcgkabp

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

Calculating rank
USPTO Granted Patents = 8 

% Patents Active = 87.5

 

Average Co-Inventor Count = 5.8

ph-index = 1

Forward Citations = 3(Granted Patents)


Company Filing History:


Years Active: 2024-2026

Loading Chart...
Loading Chart...
8 patents (USPTO):Explore Patents

Title: Yikai Wang: Innovator in 3D Scene Reconstruction

Introduction

Yikai Wang is a prominent inventor based in Beijing, China. He has made significant contributions to the field of image processing and 3D scene reconstruction. With a total of five patents to his name, Wang's work showcases his innovative approach to technology.

Latest Patents

One of Yikai Wang's latest patents is a system and method for reconstructing 3D scene data from 2D image data. This invention involves a method and apparatus that utilizes a fully-differentiable transformer-based encoder-decoder to reconstruct a three-dimensional scene from a two-dimensional input image. The process begins with encoding the 2D input image into a set of image features using a pre-trained vision transformer model. This model is pre-trained with multi-view RGB image supervision and point cloud supervision. The encoded features are then projected onto a 3D triplane representation using a transformer decoder, resulting in output triplane tokens. The geometry of the generated 3D asset is represented with a surface mesh, which includes vertices and triangular faces. Additionally, a texture map is created with a multichannel image in UV space, allowing for multiple views of the 3D scene to be generated simultaneously.

Another notable patent by Wang is an input image size switchable network for adaptive runtime efficient image classification. This invention discusses techniques related to implementing and training image classification networks. These techniques include applying shared convolutional layers to input images regardless of resolution and selectively applying normalization based on the input image resolution. Furthermore, the training process involves mixed image size parallel training and mixed image size ensemble distillation.

Career Highlights

Yikai Wang has worked with notable companies such as Intel Corporation and Futureverse IP Limited. His experience in these organizations has contributed to his expertise in the field of technology and innovation.

Collaborations

Wang has collaborated with talented individuals, including Anbang Yao and Ming Lu. These collaborations have likely enriched his work and led to further advancements in his projects.

Conclusion

Yikai Wang is a distinguished inventor whose work in 3D scene reconstruction and image classification has made a significant impact in the field of technology. His innovative patents and collaborations highlight his dedication to advancing the industry.

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…