17840571. SYSTEMS AND METHODS OF AUTOMATED IMAGING DOMAIN TRANSFER simplified abstract (QUALCOMM Incorporated)
SYSTEMS AND METHODS OF AUTOMATED IMAGING DOMAIN TRANSFER
Organization Name
Inventor(s)
Ajit Deepak Gupte of Bangalore (IN)
Chiranjib Choudhuri of Bangalore (IN)
SYSTEMS AND METHODS OF AUTOMATED IMAGING DOMAIN TRANSFER - A simplified explanation of the abstract
This abstract first appeared for US patent application 17840571 titled 'SYSTEMS AND METHODS OF AUTOMATED IMAGING DOMAIN TRANSFER
Simplified Explanation
The patent application describes an imaging system that can capture images of a user in a specific pose or facial expression. The system uses an image sensor to capture the images in a first electromagnetic frequency domain, such as infrared or near-infrared. These images are then processed by trained machine learning models to generate a representation of the user in a second electromagnetic frequency domain, such as visible light. The system outputs this representation of the user in the desired pose or expression.
- The imaging system captures images of a user in a specific pose or facial expression.
- The images are captured in a first electromagnetic frequency domain, such as infrared or near-infrared.
- Trained machine learning models are used to process the images and generate a representation of the user in a second electromagnetic frequency domain, such as visible light.
- The system outputs the representation of the user in the desired pose or expression.
Potential Applications
- Facial recognition systems
- Virtual reality and augmented reality applications
- Gaming and animation industry
- Biometric identification systems
Problems Solved
- Capturing images of a user in a specific pose or expression
- Converting images from one electromagnetic frequency domain to another
- Generating accurate representations of users based on image data
Benefits
- Improved accuracy in capturing and representing user poses and expressions
- Enhanced capabilities in facial recognition and identification systems
- Increased realism in virtual reality and augmented reality applications
- More efficient and effective animation and gaming experiences
Original Abstract Submitted
Imaging systems and techniques are described. An imaging system receives, from an image sensor, image(s) of a user (e.g., in a pose and/or with a facial expression). The image sensor captures the first set of image(s) in a first electromagnetic (EM) frequency domain, such as the infrared and/or near-infrared domain. The imaging system generates a representation of the user in the first pose in a second EM frequency domain (e.g., visible light domain) at least in part by inputting the image(s) into one or more trained machine learning models. The representation of the user is based on an image property associated with image data of at least the part of the user in the second EM frequency domain. The imaging system outputs the representation of the user in the pose in the second EM frequency domain.
