Search

Under severe weather conditions, the quality of the images taken outside is directly affected by floating atmospheric particles. To keep the quality of the images, haze removal methods play a critical role. The most difficult part of haze removal is removing the haze that spreads over the entire image. Many CNN-based methods have been proposed to remove the haze, and can be divided into two types. One is to use a multi-scale structure and the other is to stack layers. The former causes image degradation due to the loss of some of the original information in an image and the latter increases computational complexity due to not reducing the resolution. In addition, a large number of parameters is required to secure the expressive power of the model, which leads to a huge amount of memory. To tackle these problems, we tried to 1) downsample the image while saving parameters and maintaining the quality of the generated image, and 2) consider the information in the entire image to remove the haze. For the first problem, we tried to solve this by using a feature extractor that has been used in other tasks, learning to optimize the output image in low-resolution, and preparing kernels with various dilation rates to expand the receptive fields. For the second problem, we use the attention structure to determine which part of the image features should be focused on from the entire feature map. By incorporating such modules, our method achieves better results on both synthetic and real-world images when compared with state-of-the-art methods.

Amacrine interneurons, which are highly diversified in morphological, neurochemical, and physiological features, play crucial roles in visual information processing in the retina. However, the specification mechanisms and functions in vision for each amacrine subtype are not well understood. We found that the Prdm13 transcriptional regulator is specifically expressed in developing and mature amacrine cells in the mouse retina. Most Prdm13-positive amacrine cells are Calbindin- and Calretinin-positive GABAergic or glycinergic neurons. Absence of Prdm13 significantly reduces GABAergic and glycinergic amacrines, resulting in a specific defect of the S2/S3 border neurite bundle in the inner plexiform layer. Forced expression of Prdm13 distinctively induces GABAergic and glycinergic amacrine cells but not cholinergic amacrine cells, whereas Ptf1a, an upstream transcriptional regulator of Prdm13, induces all of these subtypes. Moreover, Prdm13-deficient mice showed abnormally elevated spatial, temporal, and contrast sensitivities in vision. Together, these results show that Prdm13 regulates development of a subset of amacrine cells, which newly defines an amacrine subtype to negatively modulate visual sensitivities. Our current study provides new insights into mechanisms of the diversification of amacrine cells and their function in vision. [ABSTRACT FROM AUTHOR]