CNN阴影去除--DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal
来源:互联网 发布:笔记本网卡mac地址修改 编辑:程序博客网 时间:2024/06/07 22:18
DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal
CVPR2017
本文使用深度学习CNN网络来进行阴影去除,最大的特色就是全自动的端对端的实现阴影去除。 automatic and end-to-end deep neural network (DeshadowNet)
阴影去除也算是一个老大难问题了,目前存在的方法主要问题有如下三点:
1)Lack of a fully-automatic and end-to-end pipeline
2)Neglect high level semantic information, 目前大部分算法采用 low-level 特征, color ratios,color statistics 。但是阴影同样与 semantic contents 高度相关 (例如 geometry and material)
3)Require specific operation for penumbra regions 对于半阴影区域需要特别操作
针对阴影去除,目前还没有很好的数据库,我们自己建立了一个较大数据库
3 A New Dataset for Shadow Removal – SRD
自己拍照搞了 3088 图像对,主要考虑以下四个因素:Illumination,Scene,Reflectance,Silhouette
我们提出的 DeshadowNet 是 multi-context的,它综合 high-level semantic information, mid-level appearance information and local image details 这些信息来进行最终的预测, 这个 multi-context embedding 是通过三个子网络来实现的: global localization network (G-Net), appearance modeling network (A-Net), and semantic modeling network (S-Net)
G-Net 提取阴影特征表示来描述 场景中的全局结构和 high-level semantic context
G-Net extracts shadow feature representation to describe the global structure and high-level semantic context of the scene
A-Net 提取 G-Net 浅层中的 appearance 信息
A-Net acquire the appearance information from the shallower layer of G-Net
S-Net 提取 G-Net 深层中的 semantic 信息
S-Net acquire the semantic information from the deeper layer of G-Net
本文提出的网络结构
本文提出的网络结构中间结果的显示
网络模型参数设置
损失函数定义
我们采用了 Mean Squared Error (MSE) as the loss function in the log space
Training strategy
为了防止过拟合,我们采用以下训练策略:
1)Multi-stage training strategy 多阶段训练,先分开训练G-Net+A-Net and G-Net+S-Net,然后再整体训练
2) Multi-size training strategy 多尺度训练, coarse scale 64 × 64, medium scale 128 × 128, and fine scale 224 × 224
3)Data synthesis 合成更多的训练数据,60,000 640×480
4)Data augmentation 包括 image translations, flipping and cropping
- CNN阴影去除--DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal
- A Multi-task Deep Network for Person Re-identification
- Deep Network Flow for Multi-Object Tracking
- CANE-Context-Aware Network Embedding for Relation Modeling论文学习
- 论文笔记 MSCNN:A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- MSCNN 论文解析(A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- MSCNN 论文解析(A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- [论文解读] MSCNN: A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- 目标检测--A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- 阅读A Discriminatively Learned CNN Embedding for Person Re-identification
- A Lightened CNN for Deep Face Representation
- Multi-column deep neural network for traffic sign classification
- 论文笔记之Structural Deep Network Embedding
- 快速去阴影--Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
- 【Person Re-id】A Discriminatively Learned CNN Embedding for Person Re-identification
- [Paper note] Embedding Deep Metric for Person Re-identification: A Study Against Large Variation
- 立体匹配之(三): A Deep Visual Correspondence Embedding Model for Stereo Matching Costs
- Embedding Deep Metric for Person Re-identification: A Study Against Large Variations
- CentOS 6.5下安装MySQL 5.6
- Git远程操作详解
- 外观模式
- Java中boolean类型占用多少个字节
- Solr集群搭建
- CNN阴影去除--DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal
- 欢迎使用CSDN-markdown编辑器
- nginx+openssl配置https协议需要注意的问题
- 计算机考试干货,are you ready?
- 计算机的基本组成及工作原理(1)
- Judge Route Circle
- XML与DataSet的相互转换的类
- 《并发编程》--9.线程安全和synchronizd关键字
- 欢迎使用CSDN-markdown编辑器