机译:基于各向异性的图像平滑通过深度神经网络培训
Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Guangdong Peoples R China;
Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Guangdong Peoples R China;
Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Guangdong Peoples R China|Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Guangdong Peoples R China;
image texture; neural nets; edge detection; image denoising; optimisation; image enhancement; smoothing methods; anisotropy-based measurement; anisotropy degree; edge pixel; larger anisotropy; structural edges; deep network; smoothed images; deep neural network training; anisotropy-based image smoothing method; image details; image structure;
机译:使用松散和弱标记的图像训练无线传感器网络的深度神经网络
机译:基于MR图像的带有生成对抗网络的深度神经网络预训练用于脑肿瘤分类
机译:通过深神经网络和概率图形模型对皮肤镜图像的光滑和无噪声界面分割
机译:更深入的图像质量传递:训练用于3D图像的低内存神经网络
机译:具有深层神经网络的自然图像中的强大文本斑点
机译:具有深神经网络的视网膜眼底图像的糖尿病视网膜病评级的非均匀标记平滑
机译:更深的图像质量转移:培训3D图像的低记忆神经网络