Internship: Deep Learning for Removing Clouds from Satellite Images

MERL is looking for an intern to carry out research on removing clouds from satellite images. The focus will be on creating innovative deep learning algorithms for this use. An ideal candidate would be a PhD student with expertise in deep learning and computational imaging, with a record of publications. A background and experience in deep image restoration algorithms, for example, deep algorithm unraveling, and the use of deep priors like diffusion models are highly desired. Proficiency in Python and Pytorch is mandatory. The intern is expected to publish the research findings in a conference or journal. The internship is expected to last for three months, with a flexible start date. Research Areas: Computational Sensing, Computer Vision, Machine Learning, Signal Processing Contact: Suhas Lohit Mitsubishi Electric Research Labs, Inc. "MERL" provides equal employment opportunities (EEO) to all employees and applicants for employment regardless of their race, color, religion, sex, national origin, age, disability, or genetics. In compliance with federal law requirements, MERL adheres to applicable state and local laws that prohibit discrimination in employment in every location where the company has facilities. This policy applies to all aspects of employment, including recruitment, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, and training. MERL expressly forbids any form of workplace harassment based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status. Inappropriate interference with MERL's employees' ability to do their jobs could lead to disciplinary actions up to and including dismissal. Being employed at MERL demands full authorization to work in the U.S and access to technology, software, and other information subject to government access control restrictions, due to export controls. Employment depends on maintaining full authorization to work in the U.S and the availability of government authorization for the release of certain items, which may necessitate obtaining an export license or other documentation. MERL may postpone starting employment, withdraw a job offer, terminate employment, and/or adjust job responsibilities, compensation, benefits, and access to MERL facilities and information systems, as MERL deems necessary, to ensure practical adherence to applicable employment laws and government access control restrictions.