|
Sean ManI am a PhD student at the Technion – Israel Institute of Technology, where I conduct research in the GIP Lab in the Computer Science Department and am enrolled in the Technion Autonomous Systems Program (TASP). My research focuses on solving image inverse problems (image restoration) under realistic settings, such as unknown degradations or the use of latent priors. My PhD advisor is Prof. Miki Elad. My work studies Bayesian approaches to image restoration with an emphasis on high perceptual quality, including sampling from posterior distributions. I am particularly interested in diffusion models and their use as expressive priors for inverse problems under real-world conditions. In the summer of 2025, I was an Applied Scientist Intern at Amazon AWS, where I worked on masked discrete diffusion models for vision–language tasks, with a primary focus on OCR. I have served as a teaching assistant for the course Numerical Algorithms for six semesters and was awarded Outstanding Teaching Assistant for three consecutive semesters. Email / GitHub / Google Scholar / LinkedIn |
ResearchI'm interested in computer vision, machine learning, optimization, graphics and visual effects. |
|
ELAD: Blind Face Restoration using Expectation-based Likelihood Approximation and Diffusion Prior, Guy Ohayon, Ron Raphaeli, Matan Kleiner, Michael Elad SIGGRAPH Asia, 2025 arxiv • acm • website • We propose a novel approach to blind face restoration using a degradation estimator, expectation-based likelihood approximation, and diffusion prior. |
|
SILO: Solving inverse problems with latent operatorsRon Raphaeli, , Michael Elad ICCV, 2025 arxiv • cvf • talk • code • website • We propose a novel approach to solving inverse problems with latent diffusion models by training an extremely small latent operator to mimic the degradation operator. |
|
High-perceptual quality JPEG decoding via posterior sampling 🏅, Guy Ohayon, Theo Adrai, Michael Elad CVPRW, 2023 Sony Best Paper Award arxiv • cvf • We propose a novel Bayesian approach to JPEG decoding that leverages posterior sampling to improve the perceptual quality of the decoded image. |
|
Design and source code from Jon Barron's website and Leonid Keselman |