Image translation tasks based on generative models have become an important research area, such as the general framework for unsupervised image translation-CycleGAN (Cycle-Consistent Generative Adversarial Networks). A typical advantage of CycleGAN is that it can realize the training of two image sets without pairing, but there are still some problems in the preservation of semantic information and the learning of specific features. In this paper, we propose the CycleGAN-AdaIN framework based on the CycleGAN model, which can translate real photos into Chinese ink paintings. In order to retain the content of the image completely, we use one cycle consistency loss to replace two in the structure of the model. To learn the style information of the ink painting, we introduce an AdaIN (Adaptive Instance Normalization) module before the decoding process of the generation network. In addition, to correct the details of the generated image, we add the MS-SSIM (Multi-Scale-Structural Similarity Index) loss in the reconstruction loss to generate a higher quality image. Compared with the existing methods in FID, Kernel MMD, PSNR and SSIM, the experiment results show that our method can accomplish the task of transferring real photos to ink paintings and get better performance than the baseline model.
14 March 2018 in International Journal of Pattern Recognition and Artificial Intelligence
Objective: To determine the effect of mitochondrial DNA copy number (mtDNAcn) as a biomarker of benzene exposure. Methods: A total of 294 benzene-exposed workers and 102 controls were recruited. Biomarkers of mtDNAcn, cytokinesis-block micronucleus (MN) frequency, and peripheral blood white blood cells (WBC) were detected. Eighteen polymorphism sites in DNA damage repair and metabolic genes were analyzed. Results: Benzene exposure increased mtDNAcn and indicated a dose–response relationship (P < 0.001). mtDNAcn was negatively correlated with WBC count and DNA methylation and positively correlated with MN frequency. The AG type in rs1695 interacted with benzene exposure to aggravate mtDNAcn (β = 0.006, 95% CI: 0, 0.012, P = 0.050). rs13181, rs1695, rs1800975, and GSTM1 null were associated with benzene-induced mtDNAcn. Rs1695 interacted with benzene to increase mitochondrial damage. Conclusions: Benzene exposure increases mtDNAcn levels in benzene-exposed workers.
1 July 2021 in Computers and Electrical Engineering
Along with the continuous development of urbanization, the development of modern cities has led to the following problems: 1. The natural environment is destroyed in large quantities, forming the confrontation between man and nature 2. The parts of the cities are far from the natural environment Therefore, in view of the long-term development of human beings and urban construction, with the construction of the idea about the planning tradition of landscapes and culture[1], we design a project that takes the natural landscape and the beauty of the city into account, which is called Urban Town, and provides a design idea for the construction of a new city. Urban Town is composed of several regions, including urban areas and rural areas. Urban Town is a fictional urban area, which aims to plan under the premise of integrating natural landscape. The urban design can carry out the transformation of natural environment residence and work properly according to the actual demand. Residents can enjoy natural beauty and improve their life experience. We rendered the scene by designing the scene using the realtime rendering software TwinMotion. We designing and making architectural models in blender and sketchup, importing the model into TwinMotion and giving the model a map material.