Students
I am currently a Masters student in Computer Vision at The Robotics Institute at Carnegie Mellon University.
Responsibilities : RGB Conditioning for Deep Image Prior (DIP), Dimensionality Reduction for DIP, Theoretical Analysis for DIP
I am currently a Masters student in Computer Vision at The Robotics Institute at Carnegie Mellon University.
I am interested in the intersection of Geometry and Deep Learning for applications such as SLAM, Super-Resolution, 3D Reconstruction.
Previously I have worked in : Structured Light, 3D Reconstruction, Imaging Pipelines, Tracking, OCR, NIR Imaging [ Computer Vison ]; and Compilers and Grammars [ Systems, Programming Languages]
Responsibilities : Network Quantization in DIP, Theoretical Analysis for DIP
Advisor
Simon Lucey
I am an associate research professor within the Robotics Institute at Carnegie Mellon University, where I am part of the Computer Vision Group, and leader of the CI2CV Lab. Before returning to CMU I was a Principle Research Scientist at the CSIRO (Australia’s premiere government science organization) for 5 years.
A central goal of mine long term is to stay true, in terms of research and industry engagement, to the grand goals of computer vision as a scientific discipline. I believe these goals to be strongly correlated with the founding philosophy of the Robotics Institute itself (i.e. of deep understanding for systems that work) . Specifically, although we want to develop seeing machines that work that work and have societal/economic impact, we do not want to replace “understanding” for “data”. Instead we want to draw inspiration from vision researchers of the past to attempt to unlock computational and mathematic models that underly the processes of visual perception using machine learning as a tool not a replacement.