红枫归尘-CSDN博客

原创【论文笔记】Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization

Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance NormalizationAbstractIntroductionMethodsomething moreAbstract提出泛化性较强的去噪结构和一种迁移学习策略。用自适应实例规范化（Adaptive Instance Normalization）来搭建去噪器，可以约束feature map，防止网络过拟合。Introduction先分析了

2020-05-25 11:34:12 1842 1

原创【论文笔记】Learning Enriched Features for Real Image Restoration and Enhancement

Learning Enriched Features for Real Image Restoration and EnhancementAbstractContributionMethod（MIRNet）Abstract先讲述高质量图像获取的广泛应用和重要性。CNN的方法主要在全分辨率或者低分辨率表达上应用，前者在空域上效果优良但缺少连贯性的鲁棒结果，后者语义可靠但空域上缺乏精确结果。本文提...

2020-05-08 19:50:16 3533 3

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

原创 【论文笔记】Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization

原创 【论文笔记】Learning Enriched Features for Real Image Restoration and Enhancement

空空如也

空空如也

原创【论文笔记】Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization

原创【论文笔记】Learning Enriched Features for Real Image Restoration and Enhancement