Single image mixed dehazing method based on numerical iterative model and DehazeNet.

As one of the most common adverse weather phenomena, haze has caused detrimental effects on many computer vision systems. To eliminate the effect of haze, in the field of image processing, image dehazing has been studied intensively, and many advanced dehazing algorithms have been proposed. Physical model-based and deep learning-based methods are two competitive methods for single image dehazing, but it is still a challenging problem to achieve fidelity and effectively dehazing simultaneously in real hazy scenes. In this work, a mixed iterative model is proposed, which combines a physical model-based method with a learning-based method to restore high-quality clear images, and it has good performance in maintaining natural attributes and completely removing haze. Unlike previous studies, we first divide the image into different regions according to the density of haze to accurately calculate the atmospheric light for restoring haze-free images. Then, dark channel prior and DehazeNet are used to jointly estimate the transmission to promote the final clear haze-free image that is more similar to the real scene. Finally, a numerical iterative strategy is employed to further optimize the atmospheric light and transmission. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods on synthetic datasets and real-world datasets. Moreover, to indicate the universality of the proposed method, we further apply it to the remote sensing datasets, which can also produce visually satisfactory results.

Anatomical and Functional Outcomes in Eyes with Idiopathic Macular Holes that Underwent Surgery Using the Inverted Internal Limiting Membrane (ILM) Flap Technique Versus the Conventional ILM Peeling Technique.

INTRODUCTION: To evaluate the anatomical and functional outcomes of the inverted internal limiting membrane (ILM) flap technique (IFT) in macular holes (MHs), especially in MHs with a macular hole index (MHI) < 0.5. METHODS: This was a retrospective comparative study. Patients with idiopathic MHs who underwent either the IFT or conventional ILM peeling (CP) were investigated. The main outcomes included the MH closure rate, best corrected visual acuity (BCVA), and recovery rates of the external limiting membrane (ELM) and ellipsoid zone (EZ) at 1, 3, and 6 months postoperatively. RESULTS: Forty-eight eyes of 48 patients who underwent the IFT (n = 29, Group A) or CP (n = 19, Group B) were included. The mean minimal diameter was 522.00 ± 208.08 µm. The closure rate was 100.0% in Group A and 94.7% in Group B (P = 0.396). The mean BCVA and EZ and ELM recovery rates improved significantly in both groups postoperatively. No significant differences in BCVA or the EZ or ELM recovery rates were found between the two groups. Of the 39 eyes whose MHI was < 0.5, 25 underwent the IFT, and 14 underwent CP. Comparing the results of the closure rate, BCVA and recovery rates of the EZ and ELM between groups were similar to those in 48 eyes. CONCLUSION: Both the IFT and CP can achieve a high closure rate, with no significant difference in ordinary idiopathic MHs. The IFT does not seem to achieve better anatomical and functional outcomes than CP. The IFT should be used conservatively in ordinary non-refractory MH surgery.