Learning-based real-time method to looking through scattering medium beyond the memory effect
This addresses a practical limitation in medical imaging and other fields where scattering impedes optical imaging, though it appears incremental as it builds on existing memory effect methods.
The paper tackled the limited field-of-view problem in imaging through scattering media using the optical memory effect by proposing PDSNet, a convolutional neural network that enables accurate real-time reconstruction of scattered patterns for complex objects across various scales and media.
Strong scattering medium brings great difficulties to optical imaging, which is also a problem in medical imaging and many other fields. Optical memory effect makes it possible to image through strong random scattering medium. However, this method also has the limitation of limited angle field-of-view (FOV), which prevents it from being applied in practice. In this paper, a kind of practical convolutional neural network called PDSNet is proposed, which effectively breaks through the limitation of optical memory effect on FOV. Experiments is conducted to prove that the scattered pattern can be reconstructed accurately in real-time by PDSNet, and it is widely applicable to retrieve complex objects of random scales and different scattering media.