Plug-and-Play: A General Approach for the Fusion of Sensor and Machine Learning Models ResearchInsightsCommentarySIAM Newssiam.org FeedsComputational Science & Numerical AnalysisImaging Science Plug-and-play is a framework that incorporates modern black-box operators into regularized inversion problems.
A Denoiser Can Do Much More than Just Clean Noise ResearchInsightsCommentarySIAM Newssiam.org FeedsImaging Science Researchers are leveraging denoising algorithms to solve other, far more challenging inverse problems.
Optimal Transport for Generative Neural Networks ResearchInsightsCommentarySIAM Newssiam.org FeedsImaging ScienceOptimization The theory of optimal transport can solve problems in the unsupervised generation of text, images, and videos.
A Deeper Way to Practice Deep Learning Get InvolvedConferencesResearchInsightsCommentarySIAM Newssiam.org FeedsImaging Science The 2020 SIAM Conference on Imaging Science offered snapshots of deep learning’s impact across imaging domains.
Computational and Mobile Photography: The History of the Smartphone Camera Get InvolvedConferencesResearchInsightsCommentarysiam.org FeedsImaging Science During an IS20 minitutorial, Peyman Milanfar of Google Research explores how the mobile phone became a camera.