This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Adobe, Inc.. Active years: 2021.
Company Filing History:
Years Active: 2021
Title: Innovations by Utkarsh Singhal in Image Manipulation
Introduction
Utkarsh Singhal is an accomplished inventor based in Berkeley, CA. He has made significant contributions to the field of image processing through his innovative patent. His work focuses on utilizing deep learning techniques to enhance image manipulation processes.
Latest Patents
Utkarsh holds a patent for "Image manipulation using deep learning techniques in a patch matching operation." This method involves generating a query of a target image and keys and values from a reference image. The process includes comparing the query with each key to generate matching costs, which are then used to create a set of weights. These weights are applied to corresponding values from the reference image to produce a weighted patch. The final manipulated image is generated by applying a combined weighted patch to an image processing algorithm.
Career Highlights
Utkarsh is currently employed at Adobe, Inc., where he continues to develop innovative solutions in image processing. His expertise in deep learning and image manipulation has positioned him as a valuable asset in the tech industry.
Collaborations
He has collaborated with notable coworkers, including Connelly Barnes and Elya Shechtman, contributing to various projects that push the boundaries of image technology.
Conclusion
Utkarsh Singhal's innovative work in image manipulation showcases the potential of deep learning techniques in enhancing visual technology. His contributions are paving the way for future advancements in the field.