Introduction

1. develop a common framework for all problems that are the task of predicting pixels from pixels.

2. CNNs learn to minimize a loss function -an objective that scores the quality of results-- and although the learning process is automatic, a lot of manual effort still goes into designing effective losses.

3.the CNN to minimize Euclidean distance(欧式距离L2) between predicted and ground truth pixels, it will tend to produce blurry results.

why? because the L2 distance is minimized by averaging all plausible outputs, which cause blurring.

4.GANs learn a loss that tries to classify if the output image is real of fake ,  blurry images will not be tolerated since they obviously fake!

5. they apply cGANs suitable for image-to-image translation tasks, where we condition on input image and generate a corresponding output image.


Releted work

1.image-to-image translation problems are formulated as per-pixel(逐个像素的)classfication or regression.but these formulations treat the output space as “unstructured” ,each output pixel is considered conditionally independent from all others given the input image.(独立性!)

2. conditional GANs  learn a structured loss.

3. cGANs is different in that the loss is learned(损失可以学习), in theory,  penalize any possible structure that differs between output and target.(条件GAN的不同之处在于,损失是可以习得的,理论上,它可以惩罚产出和目标之间可能存在差异的任何结构。)

4. the choices for generator and discriminator achitecture:

for G:  using 'U-Net '

for D: using PatchGAN classifier penalizes structure at the scale of image patches. 

The purpose of PatchGAN aim to capure local style statistics.(用于捕获本地样式统计信息)


Method

1. The whole of framwork is that conditional GANs learn a mapping from observed image and random noise vector z, to y. $G:{x,z}\rightarrow y(ground-truth)$ .

 

2. Unlike an unconditional GAN, both the generator and discriminator observe the input edge map.

3. objective function:

G try to minimize this objective against an adversarial D that try to maximize it.

4. they test the importence of conditioning the disctiminator, the discriminator dose not oberve x(edge map):

5.  it's beneficial to mix GAN objective with a more traditional loss, such as L2-distance.

6. G is tasked to not only  fool the discriminator but also to be near the ground truth output in an L2 sense.

7. L1 distance is applied into the additional loss rather than L2 as L1 encourages less blurring(remeber it!).

8.

final objective

9. without $z$ (random noise vector), the net still learn a mapping from $x$ to $y$, but would produce deterministic output, therefore fail to match any distribution other than a delta function.(因此无法匹配除函数之外的任何分布)

10. towords $z$, Gaussian noise often is used in the past, but authors find this strategy ineffective, the G simply learned to ignore the noise. Finally, in the form of dropout is provided.but we observe only minor stochasticity in the output of our nets.


Network Architecture

1. The whole of generator and discriminator architectures from DCGANs.


For G: U-Net;DCGAN; encoder- decoder; bottleneck; shuttle the information;

The job:

1.mapping a high resolution grid to a high resolution output grid.

2. although the input and output differ in surface appearance, but both are rendering of same underlying structure.

The character:

structure in the input is roughly aligned with structure in the output.

The previous measures:

1.encoder-decoder network is applied.

2.until a bottleneck layer, downsample is changed to upsample.

Q:

1. A great deal of low-level information shared between the input and output, shuttling this information directly across the net is desirable.例如,在图像着色的情况下,输入和输出共享突出边缘的位置。

END:

To give the generator a means to circumvent(绕过) the bottleneck for information like this,  adding skip connections is adopted, this architecture called 'U-Net'


 The results of different loss function:

 L1 loss or L2 loss produce the blurry results on image generation problems.


 For D: 

1. both L1 and L2  produce blurry results on image generation problems.

2. L1 and L2 fail to encourage high frequency crispness(锐度),nonetheless(仍然) accurately capture  the low frequencies.

3.in order to model high-frequencies , we pay attention to the structure in local image patches.

4.This discriminator tries to classify if each patch in an N*image is real or fake. We run this discriminator convolutationally across the image, averaging all responses to provide the ultimate output of D.(这个鉴别器试图分类一个N*N图像中的每个补丁是真还是假。我们用这个判别器对图像进行卷积,对所有响应进行平均,得到D的最终输出).

5. N can be much smaller than full size of image and still produce high quality results. smaller pathGAN have mang advantages.

6. D effectively models the image as Markov random field PatchGAN cn be understand as a form of texture/ style loss!


For Optimization.

1. slows down D relative to G.(此外,在优化D时,我们将目标除以2,这减慢了D相对于G的学习速度)

2.当批大小设置为1时,这种批处理规范化方法被称为实例规范化,并被证明在图像生成任务中是有效的,

batchsize is setted into 1 to 10

3. Instance normalization(IN) and batch normalization(BN), the strategy of IN is adopted in this paper because  IN has been demonstrated to be effective at image generation task.

BN 是一个batch 里面的所有图片的均值和标准差,IN 是对一张图片求均值和标准差,shuffle的存在让batch 不稳定, 本来就相当于引入了noise, in the task of image generation, IN outperforms compared with BN, 因为这类生成式任务自己的风格较为独立不应该与batch中的其他样本产生较大的联系,相反在图像和视频的task of classification, BN outperforms IN .


 For Experiments

1. removing conditioning for D have very poor performance because  the loss does not penalize mismatch between the input and output; it only cares

that the output look realistic.

2. L1 + CGANs create realistic rendersings(渲染), L1 penalize the distance between ground truth outputs, which correctly match the input and synthesized outputs.

3.An advantage of the PatchGAN is that a fixed-size patch discriminator can be applied to arbitrarily large images.

4.

(Pixel2PixelGANs)Image-to-Image translation with conditional adversarial networks的更多相关文章

  1. image-to-image translation with conditional adversarial networks文献笔记

    Image-to-Image Translation with Conditional Adversarial Networks (基于条件gan的图像转图像) 作者:Phillip Isola, J ...

  2. 《Image-to-Image Translation with Conditional Adversarial Networks》论文笔记

    出处 CVPR2017 Motivation 尝试用条件GAN网络来做image translation,让网络自己学习图片到图片的映射函数,而不需要人工定制特征. Introduction 作者从不 ...

  3. 《Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks》论文笔记

    Code Address:https://github.com/junyanz/CycleGAN. Abstract 引出Image Translating的概念(greyscale to color ...

  4. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks 阅读笔记

    Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (使用循环一致的对抗网络的非配对图像-图 ...

  5. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks(使用循环一致的敌对网络进行不成对的图像到图像转换)

    作者:朱俊彦,朱俊彦博士是计算机图形学领域现代机器学习应用的开拓者.他的论文可以说是第一篇用深度神经网络系统地解决自然图像合成问题的论文.因此,他的研究对这个领域产生了重大影响.他的一些科研成果,尤其 ...

  6. CycleGAN --- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

    文章地址:http://openaccess.thecvf.com/content_ICCV_2017/papers/Zhu_Unpaired_Image-To-Image_Translation_I ...

  7. 语音合成论文翻译:2019_MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

    论文地址:MelGAN:条件波形合成的生成对抗网络 代码地址:https://github.com/descriptinc/melgan-neurips 音频实例:https://melgan-neu ...

  8. 生成对抗网络(Generative Adversarial Networks,GAN)初探

    1. 从纳什均衡(Nash equilibrium)说起 我们先来看看纳什均衡的经济学定义: 所谓纳什均衡,指的是参与人的这样一种策略组合,在该策略组合上,任何参与人单独改变策略都不会得到好处.换句话 ...

  9. StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation - 1 - 多个域间的图像翻译论文学习

    Abstract 最近在两个领域上的图像翻译研究取得了显著的成果.但是在处理多于两个领域的问题上,现存的方法在尺度和鲁棒性上还是有所欠缺,因为需要为每个图像域对单独训练不同的模型.为了解决该问题,我们 ...

随机推荐

  1. Python3 环境搭建 保姆式 详细教程!真手把手教学!

    本文我们将向大家介绍如何在本地搭建 Python3 开发环境. Python3 可应用于多平台包括 Windows.Linux 和 Mac OS X. Unix (Solaris, Linux, Fr ...

  2. GEKCTF2020-web

    GEKCTF [GKCTF2020]CheckIN97 <title>Check_In</title> <?php highlight_file(__FILE__); c ...

  3. keepalived+nginx集群

    https://blog.csdn.net/l1028386804/article/details/72801492?ops_request_misc=%257B%2522request%255Fid ...

  4. React 服务端渲染方案完美的解决方案

    最近在开发一个服务端渲染工具,通过一篇小文大致介绍下服务端渲染,和服务端渲染的方式方法.在此文后面有两中服务端渲染方式的构思,根据你对服务端渲染的利弊权衡,你会选择哪一种服务端渲染方式呢? 什么是服务 ...

  5. Python练习题 047:Project Euler 020:阶乘结果各数字之和

    本题来自 Project Euler 第20题:https://projecteuler.net/problem=20 ''' Project Euler: Problem 20: Factorial ...

  6. 服务器备用远程-----Radmin客户端的操作指南(如何远程与传送文件)

    一台服务器的寿命一般比较长可能会从几年到几十年,就会经历各个版本的更新与升级.再经过时间的历练后,可能windwos自带的远程连接有时候会拉胯,经常报错. 这时候就需要备选方案,有钱的单位会自己搭建堡 ...

  7. 一篇文章带你了解Java OOP思想

    Java OOP 思想深度刨析 Java面向对象编程 面向对象编程简称OOP(Object--对象.Oriendted--导向的.Programming--程序设计) 面向对象通俗来讲,就是指使用丰富 ...

  8. NOIP提高组2016 D1T2 【天天爱跑步】

    码了一个下午加一个晚上吧...... 题目描述: 小c同学认为跑步非常有趣,于是决定制作一款叫做<天天爱跑步>的游戏.<天天爱跑步>是一个养成类游戏,需要玩家每天按时上线,完成 ...

  9. C# 生成chart图表的三种方式

    .net中,微软给我们提供了画图类(system.drawing.imaging),在该类中画图的基本功能都有.比如:直线.折线.矩形.多边形.椭圆形.扇形.曲线等等,因此一般的图形都可以直接通过代码 ...

  10. docker下载速度慢,配置镜像地址

    在我们安装了docker之后,在利用docker pull下载镜像的时候,由于国内的源会出现的问题就是速度真的很慢,可以用龟速来形容因此,为了解决docker pull 拉取镜像的龟速问题,一个比较好 ...