Physics-guided foundation model for universal speckle removal in ultrathin multimode fiber imaging

TL;DR

This paper introduces SCNet, a physics-guided foundation model that enables high-fidelity speckle removal in ultrathin multimode fiber imaging, allowing for high-quality, real-time endoscopic imaging in confined spaces.

Contribution

The work presents a novel physics-guided foundation model combining MoE architecture, material-aware routing, and wavelet decomposition for universal speckle removal without target-specific retraining.

Findings

Achieves 5.66 lp/mm resolution on a USAF target

Restores fine structures on leaves and metal surfaces

Enables real-time inference at 60 FPS

Abstract

Ultrathin multimode fibers (MMFs) promise endoscopes with hair-scale diameters for accessing sub-millimeter anatomy, but in MMF far-field imaging the required small collection aperture drives speckle-dominated measurements that rapidly degrade image fidelity. Here we present Speckle Clean Network (SCNet), a physics-guided foundation model for universal speckle removal that makes photon-limited, single-fiber collection compatible with high-fidelity reconstruction across diverse scattering conditions without target-specific retraining. SCNet combines a Mixture of Experts (MoE) architecture with material-aware routing, wavelet-based frequency decomposition to separate structure from speckle across sub-bands, and a curriculum-style optimization that progressively enforces spectral consistency before spatial fidelity. Using an ultrathin dual-fiber holographic probe, we deliver wavefront-shaped illumination through one MMF and collect backscattered photons through a parallel MMF. We validate SCNet on 3D plastic objects over varying working distances, resolve 5.66 lp/mm on a paper USAF target, and restore fine structures on leaves and metal surfaces. On rabbit heart and kidney tissues, SCNet improves recovery of low-contrast anatomical texture under the same ultrathin collection constraint. We further compress SCNet through multi-teacher distillation to reduce computation while preserving reconstruction quality, enabling inference at 60 FPS. This work effectively decouples image quality from probe size, establishing a speckle-free ultrathin endoscopy for stand-off imaging in confined spaces.