Hybrid deep learning and physics-based neural network for programmable illumination computational microscopy

arXiv:2403.12970v1 Announce Type: cross
Abstract: Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong generalization capabilities while struggling with global optimization of inverse problems due to a lack of insufficient physical constraints. In contrast, deep learning methods have strong problem-solving abilities, but their generalization ability is often questioned because of the unclear physical principles. Besides, conventional deep models are …

abstract arxiv capabilities computational cs.cv deep learning eess.iv global hybrid microscopy network neural network optimization physics physics.bio-ph physics.optics sample solutions type