Differentiable Imaging: A New Tool for Computational Optical Imaging

Abstract The field of computational imaging has made significant advancements in recent years, yet it still faces limitations due to the restrictions imposed by traditional computational techniques. Differentiable programming offers a solution by combining the strengths of classical optimization and deep learning, enabling the creation of interpretable model‐based neural networks. Through the integration of physics into the modeling process, differentiable imaging, which employs differentiable programming in computational imaging, has the potential to overcome challenges posed by sparse, incomplete, and noisy data. As a result, it has the potential to play a key role in advancing the field of computational imaging and its various applications.