San Diego, CA, United States of America

Hong Cai

This inventor holds 21 USPTO granted patents and 30 published patent applications, primarily in 3D Computer Vision. Top assignee: Qualcomm Incorporated. Active years: 2025-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Hong Cai. Retrieved from https://idiyas.com/inventor/hong-cai-pq5pogw1

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

Calculating rank
USPTO Granted Patents = 21 

% Patents Active = 33.3

Average Co-Inventor Count = 5.7

ph-index = 1

Forward Citations = 1(Granted Patents)


Company Filing History:


Years Active: 2025-2026

Loading Chart...
Areas of Expertise:
Dynamic Delta Transformations
Visual Perception Tasks
Depth Completion
3D Reconstruction
Feature Reconstruction
Stereo Depth Adaptation
Semantic Segmentation
Optical Flow
Planar Mesh Reconstruction
Occlusion-aware Warping
Panoptic Segmentation
Disparity-based Refinement
21 patents (USPTO):Explore Patents

Title: Innovations of Inventor Hong Cai

Introduction

Hong Cai is a notable inventor based in San Diego, CA. He has made significant contributions to the field of technology, particularly in the areas of depth map completion and three-dimensional object part segmentation. With a total of 21 patents, his work has advanced the capabilities of visual content processing.

Latest Patents

One of his latest patents is titled "Depth map completion in visual content using semantic and three-dimensional information." This patent outlines techniques for generating fine depth maps for images of a scene based on semantic segmentation and segment-based refinement neural networks. The method involves generating a segmentation map through a segmentation neural network, which segments the scene into various regions associated with different categories. A first depth map is created based on depth measurements, followed by a second depth map generated through a depth refinement neural network. Actions can then be taken based on this refined depth map.

Another significant patent by Hong Cai is "Three-dimensional object part segmentation using a machine learning model." This patent describes systems and techniques for part segmentation, including obtaining a three-dimensional capture of an object and generating two-dimensional images from this capture. The method processes these images to create two-dimensional bounding boxes associated with parts of the object and performs three-dimensional part segmentation based on a generated point cloud and semantically labeled super points.

Career Highlights

Hong Cai is currently employed at Qualcomm Incorporated, a leading technology company known for its innovations in telecommunications and semiconductor technology. His work at Qualcomm has allowed him to explore and develop advanced technologies that enhance visual content processing.

Collaborations

Throughout his career, Hong has collaborated with notable colleagues, including Fatih Murat Porikli and Minghua Liu. These collaborations have contributed to the advancement of his research and the successful development of his patents.

Conclusion

In summary, Hong Cai is an accomplished inventor whose work in depth map completion and three-dimensional object part segmentation has made a significant impact in the field of technology. His contributions continue to influence advancements in visual content processing.

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…