首页|New Machine Learning Findings from Jiangnan University Described (A Generative M achine Learning Model for the 3d Reconstruction of Material Microstructure and P erformance Evaluation)
New Machine Learning Findings from Jiangnan University Described (A Generative M achine Learning Model for the 3d Reconstruction of Material Microstructure and P erformance Evaluation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news originating from Wuxi, People's Republi c of China, by NewsRx correspondents, research stated, "The 3D reconstruction is generally defined as the process of capturing the shape and appearance of real objects. By reconstructing 3D digital model from a series of 2D slices, it bring s considerable convenience to visualize internal structure and decipher structur e-property relation of a material." Our news journalists obtained a quote from the research from Jiangnan University , "Nowadays, the 3D reconstruction is becoming a cutting-edge technique in depic ting the internal structure and evaluating the physical performance of targeted materials. Recent years, generative machine learning methods, such as generative adversarial networks (GAN), have achieved tremendous success in AI-generated ph ysical content (AIGPC). However, lots of technical challenges remain, including oversimplified models, oversized dataset requirement and inefficient convergence . These difficulties are caused by the insufficient ability to capture detailed features and the inadequacy of the generated model quality. To this end, a novel generative model is developed, which combines the multiscale features of U-net and the synthesis ability of GANs. With the help of the multiscale channel aggre gation module, the hierarchical feature aggregation module and the convolutional block attention module, our model is developed to capture the features of the m aterial microstructure better. The loss function is refined by combining the ima ge regularization loss with the Wasserstein distance loss. In addition, the anis otropy index is adopted to measure anisotropic degree of selected samples quanti tively. The results demonstrate that the 3D structures generated by the proposed model retain high fidelity with ground truth samples."
WuxiPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningJiangnan University
NETL
NSTL
