Adaptive Inverse Mapping: A Model-free Semi-supervised Learning Approach towards Robust Imaging through Dynamic Scattering Media
Xiaowen Hu, Jian Zhao, Jose Enrique Antonio-Lopez, Stefan Gausmann,, Rodrigo Amezcua Correa, and Axel Schulzgen

TL;DR
This paper introduces an adaptive inverse mapping method for robust imaging through dynamic scattering media, capable of correcting inverse mappings with minimal prior information using unsupervised learning, demonstrated through simulations and experiments.
Contribution
The proposed AIP method is the first to adaptively correct inverse mappings in dynamic media without assuming finite sources or access to both ends.
Findings
Enhanced robustness in imaging through dynamic media.
Successful application in simulations and fiber-optic experiments.
Potential for broad use in dynamic scattering environments.
Abstract
Imaging through scattering media is a useful and yet demanding task since it involves solving for an inverse mapping from speckle images to object images. It becomes even more challenging when the scattering medium undergoes dynamic changes. Various approaches have been proposed in recent years. However, to date, none is able to preserve high image quality without either assuming a finite number of sources for dynamic changes, assuming a thin scattering medium, or requiring the access to both ends of the medium. In this paper, we propose an adaptive inverse mapping (AIP) method which is flexible regarding any dynamic change and only requires output speckle images after initialization. We show that the inverse mapping can be corrected through unsupervised learning if the output speckle images are followed closely. We test the AIP method on two numerical simulations, namely, a dynamic…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
