25 July 2026 in SSRN Electronic Journal
Underwater vision is degraded by wavelength-dependent absorption and scattering, making conventional intensity imaging unreliable for target detection and material discrimination. We report a compact snapshot spectro-polarimetric imaging system that simultaneously acquires spectral and polarization cues in a single exposure. The system stacks a 4 × 4 multispectral filter array (MSFA) with a division-of-focal-plane (DoFP) polarization sensor, providing 16 spectral channels across 430–550 nm and four linear polarization states within a 29 mm × 29 mm × 29 mm prototype. A guard-pixel extraction strategy is used to suppress spectral boundary crosstalk, and the raw mosaic frame is decoded into wavelength-resolved intensity, Stokes, and polarization-parameter images. Tank experiments in turbid water demonstrate two task-oriented capabilities: spectro-polarimetric fusion improves shell-target extraction by suppressing background leakage, while band-wise polarization descattering followed by spectral-angle-mapper (SAM) classification enhances discrimination of visually similar green materials. These results show that snapshot spectro-polarimetric imaging provides a compact and synchronous route for complex underwater vision tasks.
15 August 2026 in SSRN Electronic Journal
Underwater optical images are severely degraded by veiling backscatter, low signal-to-noise ratio, and unstable polarization measurements, especially in turbid active-illumination environments. This paper proposes a single-shot active polarimetric denoising and descattering method for underwater image restoration using a division-of-focal-plane polarization camera. Instead of estimating target-dependent polarization parameters through iterative optimization, the active polarization model is simplified by setting the target-light polarization degree to the endpoint of its valid interval. The restored target signal is then obtained by comparing the observed degree of polarization with a spatially varying backscattering-polarization field. This field is estimated from reliable target-free water regions through robust surface fitting, and can also be inferred from low-reflectance black-pixel samples when explicit water background is unavailable. To suppress noise-induced false polarization information, DoFP-BM3D denoising is introduced before Stokes reconstruction and polarization-parameter estimation. Experiments on low-polarization, high-polarization, and mixed-polarization targets under different turbidity levels demonstrate that the proposed method provides stronger background suppression, clearer target structures, and more stable quantitative performance than classical enhancement methods, conventional polarization descattering models, and recent physics-based approaches. Additional analyses show that red polarized illumination and front-end denoising further improve restoration reliability under severe scattering. The proposed framework offers a physically interpretable, non-iterative, and acquisition-efficient solution for robust underwater polarimetric perception in complex scattering environments.