Peyman is a Distinguished Scientist at Google, where he leads the Computational Imaging team. Prior to this, he was a Professor of Electrical Engineering at UC Santa Cruz for 15 years, two of those as Associate Dean for Research. From 2012-2014 he was on leave at Google-x, where he helped develop the imaging pipeline for Google Glass.
Peyman is a Distinguished Scientist at Google, where he leads the Computational Imaging team. Prior to this, he was a Professor of Electrical Engineering at UC Santa Cruz for 15 years, two of those as Associate Dean for Research. From 2012-2014 he was on leave at Google-x, where he helped develop the imaging pipeline for Google Glass.
Over the last decade, Peyman's team at Google has developed several core imaging technologies that are used in many products. Among these are the zoom pipeline for the Pixel phones, which includes the multi-frame super-resolution (Super Res Zoom) pipeline, and several generations of state of the art digital upscaling algorithms. Most recently, his team led the development of Unblur, and Zoom Enhance features launched in Google Photos and Pixel devices.
Over the last decade, Peyman's team at Google has developed several core imaging technologies that are used in many products. Among these are the zoom pipeline for the Pixel phones, which includes the multi-frame super-resolution (Super Res Zoom) pipeline, and several generations of state of the art digital upscaling algorithms. Most recently, his team led the development of Unblur, and Zoom Enhance features launched in Google Photos and Pixel devices.
Peyman received his undergraduate education in electrical engineering and mathematics from the UC Berkeley, and the MS and PhD degrees in electrical engineering from MIT. He holds more than two dozen patents. He founded MotionDSP, which was acquired by Cubic Inc.
Peyman received his undergraduate education in electrical engineering and mathematics from the UC Berkeley, and the MS and PhD degrees in electrical engineering from MIT. He holds more than two dozen patents. He founded MotionDSP, which was acquired by Cubic Inc.
Along with his students and colleagues, his research work has had deep impact in several areas of computational imaging, and applications of AI thereto - including the introduction of adaptive kernel regression to imaging; pioneering use of learning for fast, content-adaptive image upscaling (RAISR); Neural Image quality Assessment (NIMA), Regularization by Denoising (RED); and most recently (2024) Inversion by Direct Iteration (InDI). All of these works have been recognized with best paper awards.
Along with his students and colleagues, his research work has had deep impact in several areas of computational imaging, and applications of AI thereto - including the introduction of adaptive kernel regression to imaging; pioneering use of learning for fast, content-adaptive image upscaling (RAISR); Neural Image quality Assessment (NIMA), Regularization by Denoising (RED); and most recently (2024) Inversion by Direct Iteration (InDI). All of these works have been recognized with best paper awards.
He's been a Distinguished Lecturer of the IEEE Signal Processing Society, and is a Fellow of the IEEE "for contributions to inverse problems and super-resolution in imaging"
He's been a Distinguished Lecturer of the IEEE Signal Processing Society, and is a Fellow of the IEEE "for contributions to inverse problems and super-resolution in imaging"
New: Denoisers are very important, and there's no standard reference to learn about them. They are now used to solve far bigger problems than just noise reduction - in imaging, inverse problems, & machine learning. As such their importance has grown significantly. We wrote this work as an overview (not a survey) with focus on ideal denoisers, their properties, & connections to statistical theory & machine learning. We demonstrate how denoisers can serve as fundamental building blocks in many applications.
New: Denoisers are very important, and there's no standard reference to learn about them. They are now used to solve far bigger problems than just noise reduction - in imaging, inverse problems, & machine learning. As such their importance has grown significantly. We wrote this work as an overview (not a survey) with focus on ideal denoisers, their properties, & connections to statistical theory & machine learning. We demonstrate how denoisers can serve as fundamental building blocks in many applications.
@article{milanfar2024denoising, title={Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning}, author={Peyman Milanfar and Mauricio Delbracio}, year={2024}, journal={Philosophical Transactions of the Royal Society A}, publisher={Royal Society Publishing} url={https://arxiv.org/abs/2409.06219}, }
