Company Filing History:
Years Active: 2021-2025
Title: Tadas Baltrusaitis: Innovator in Keypoint Regression and Physio-Realistic Avatars
Introduction
Tadas Baltrusaitis is a prominent inventor based in Cambridge, GB. He has made significant contributions to the fields of computer vision and machine learning, holding a total of 10 patents. His innovative work focuses on model fitting using keypoint regression and the generation of physio-realistic avatars.
Latest Patents
One of Tadas Baltrusaitis's latest patents involves model fitting using keypoint regression. In this invention, keypoints are predicted in an image, with predictions generated for each keypoint as a 2D random variable, normally distributed with location (x, y) and standard deviation sigma. A neural network is trained to maximize a log-likelihood that samples from each of the predicted keypoints equal a ground truth. This trained neural network can then predict keypoints of an image without generating a heatmap.
Another notable patent focuses on generating physio-realistic avatars for training non-contact models to recover physiological characteristics. This system provides methods for generating video sequences that include physio-realistic avatars. In this process, an albedo for an avatar is received, and a sub-surface skin color associated with the albedo is modified based on physiological data. The rendered avatar can then be synthesized in a video frame, which may be used to train a machine learning model to detect a physiological characteristic.
Career Highlights
Tadas Baltrusaitis is currently employed at Microsoft Technology Licensing, LLC, where he continues to push the boundaries of innovation in technology. His work has garnered attention for its practical applications in various fields, including healthcare and artificial intelligence.
Collaborations
He collaborates with talented individuals such as Matthew Alastair Johnson and Marek Adam Kowalski, contributing to a dynamic and innovative work environment.
Conclusion
Tadas Baltrusaitis is a leading inventor whose work in keypoint regression and physio-realistic avatars is shaping the future of technology. His contributions are paving the way for advancements in machine learning and computer vision.
Inventor’s Patent Attorneys refers to legal professionals with specialized expertise in representing inventors throughout the patent process. These attorneys assist inventors in navigating the complexities of patent law, including filing patent applications, conducting patent searches, and protecting intellectual property rights. They play a crucial role in helping inventors secure patents for their innovative creations.