Low-light enhancement method with dual branch feature fusion and learnable regularized attention.

Restricted by the lighting conditions, the images captured at night tend to suffer from color aberration, noise, and other unfavorable factors, making it difficult for subsequent vision-based applications. To solve this problem, we propose a two-stage size-controllable low-light enhancement method, named Dual Fusion Enhancement Net (DFEN). The whole algorithm is built on a double U-Net structure, implementing brightness adjustment and detail revision respectively.

Full Stokes polarimetry based on an inverse-designed multi-foci metalens.

In the realm of metasurface-based polarimetry, well-known for its remarkable compactness and integration capabilities, previous attempts have been hindered by limitations such as the restricted choices of target polarization states and the inefficient focusing of light. To address these problems, this study introduces and harnesses a novel, to our knowledge, forward-solving model, grounded in the equivalence principle and dyadic Green's function, to inversely optimize the vectorial focusing patterns of metalenses. Leveraging this methodology, we develop and experimentally validate a single multi-foci metalens-based polarimeter, capable of simultaneously separating and concentrating four distinct elliptical polarization states at a wavelength of 10.

Research on a multi-dimensional image information fusion algorithm based on NSCT transform.

Traditional inspection cameras determine targets and detect defects by capturing images of their light intensity, but in complex environments, the accuracy of inspection may decrease. Information based on polarization of light can characterize various features of a material, such as the roughness, texture, and refractive index, thus improving classification and recognition of targets. This paper uses a method based on noise template threshold matching to denoise and preprocess polarized images.