No-Reference Image Quality Assessment by Hallucinating Pristine Features.

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination. The proposed quality assessment framework is rooted in the view that the perceptually meaningful features could be well exploited to characterize the visual quality, and the natural image statistical behaviors are exploited in an effort to deliver the accurate predictions. Herein, the PR features from the distorted images are learned by a mutual learning scheme with the pristine reference as the supervision, and the discriminative characteristics of PR features are further ensured with the triplet constraints. Given a distorted image for quality inference, the feature level disentanglement is performed with an invertible neural layer for final quality prediction, leading to the PR and the corresponding distortion features for comparison. The effectiveness of our proposed method is demonstrated on four popular IQA databases, and superior performance on cross-database evaluation also reveals the high generalization capability of our method. The implementation of our method is publicly available on https://github.com/Baoliang93/FPR.

Accurate aberration correction in confocal microscopy based on modal sensorless method.

Confocal microscopy has the advantages of high resolution and optical sectioning ability over conventional microscopy. However, aberration induced by the optical system can compromise these advantages and considerably reduce the energy reaching the pointlike detector. We propose an accurate aberration correction method with a liquid-crystal spatial light modulator (LCSLM) in the confocal system. Each coefficient of Zernike aberration modes is calculated by directly measuring the variance of the images with different bias aberration modes. Large-coefficient (>0.7 rad) aberration is compensated first by LCSLM, following which aberrations with small coefficients are measured precisely, minimizing the cross talk between different kinds of aberrations. With this predistortion strategy, the aberration correction is much more accurate, and maximum image intensity in the normal and nonconjugated systems is improved by 2.5 times and 4 times compared to the normal correction method, respectively, demonstrating the effectiveness of our method.

Artifact-free, penetration-adjustable elliptical-mirror-based TIRF microscopy.

Evanescent field distribution in the focal region of the elliptical-mirror-based total-internal-reflection fluorescence (e-TIRF) microscopy is analyzed based on vectorial diffraction theory. The simulation demonstrates that the intensity of an evanescent field generated by elliptical mirror decreases exponentially with the penetration depth, and the polarization characteristic of the evanescent wave in various directions is given. We build up an e-TIRF microscope utilizing a focused hollow-cone illumination with all-direction and large range of incidence. The experiment shows the artifact effect can be well suppressed by using the azimuthal-direction illumination method. In addition, the penetration depth of the evanescent field can be controlled by adjusting the sizes of the aperture and obstruction with a large range.