博客地址：http://www.globm.top/blog/1/detail/29

vue cli3配置image-webpack-loader对图片进行压缩优化
安装
npm install image-webpack-loader --save-dev

配置vue.config.js
chainWebpack: config => {
    config.plugins.delete('prefetch')
    config.plugin('provide').use(webpack.ProvidePlugin, [{
      $: 'jquery',
      jquery: 'jquery',
      jQuery: 'jquery',
      'window.jQuery': 'jquery'
    }])
    config.module.rule('images')
      .test(/\.(png|jpe?g|gif|svg)(\?.*)?$/)
      .use('image-webpack-loader')
      .loader('image-webpack-loader')
      .options({ bypassOnDebug: true })
  }

重启项目打包 ok

Supervised




Note
Model
Paper
Conference
paper link
code link





pix2pix
Image-to-Image Translation with Conditional Adversarial Networks
CVPR 2017
1611.07004
junyanz/pytorch-CycleGAN-and-pix2pix


texture guided
TextureGAN
TextureGAN: Controlling Deep Image Synthesis with Texture Patches
CVPR 2018
1706.02823
janesjanes/Pytorch-TextureGAN



Contextual GAN
Image Generation from Sketch Constraint Using Contextual GAN
ECCV 2018
1711.08972




pix2pix-HD
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
CVPR 2018
1711.11585
NVIDIA/pix2pixHD


one-to-many
BicycleGAN
Toward Multimodal Image-to-Image Translation
NIPS 2017
1711.11586
junyanz/BicycleGAN


keypoint guided
G2-GAN
Geometry Guided Adversarial Facial Expression Synthesis
MM 2018
1712.03474




contour2im
Smart, Sparse Contours to Represent and Edit Images
CVPR 2018
1712.08232
website


disentangle
Cross-domain disentanglement networks
Image-to-image translation for cross-domain disentanglement
NIPS 2018
1805.09730



gesture
GestureGAN
GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
MM 2018
1808.04859
Ha0Tang/GestureGAN


video
vid2vid
Video-to-Video Synthesis
NIPS 2018
1808.06601
NVIDIA/vid2vid


video
pix2pix-HD + Temporal Smoothing + faceGAN
Everybody Dance Now
ECCVW 2018
1808.07371
website


(un)supervised
MSGAN
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
CVPR 2019
1903.05628
HelenMao/MSGAN


semantic to image
SPADE
Semantic Image Synthesis with Spatially-Adaptive Normalization
CVPR 2019
1903.07291
NVlabs/SPADE


Edge and color domain to reconstrcut image
PI-REC
PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain

1903.10146
youyuge34/PI-REC


Cross-view image translation
SelectionGAN
Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
CVPR 2019
1904.06807
Ha0Tang/SelectionGAN


keypoint guided
C2-GAN
Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
MM 2019
1908.00999



Few shot, video
Few-shot vid2vid
Few-shot Video-to-Video Synthesis
NeurIPS 2019
1910.12713
NVlabs/few-shot-vid2vid

Image

Property:
			
Function:
		
Source Image
			
用于展示的纹理图片 (类型必须是Sprite).
		
Color
			
给图片混合上颜色（可以用来改变明暗，色调）
		
Material
			
图片渲染材质
		
Raycast Target
			
能否作为射线碰撞的目标
		
Preserve Aspect
			
确保图片保持当前的长宽比
		
Set Native Size
			
设置GameObject为原本的像素大小（使Width\Height等于原像素宽度\高度）
		
Image Type
			
图片的显示类型（填充GameObject）:Simple（拉伸填充）,Slice（边界切分，缩放时仅对边界内图缩放去填充，用于背景图）,Tiled（铺地砖式填充）,Filled（填充一部分，可设置填充方式，起点，进度，用于做技能CD效果图）。
		
 

RawImage

属性
			
作用
		
Textture
			
用于展示的纹理图片 (任意类型）
		
Color
			
同Image
		
Material
			
同Image
		
Raycast Target
			
同Image
		
UV Rect
			
设置UV缩放，偏移（即只让图片显示一部分，可使用图集）
		
 

两者最大的差别在于展示的texture是sprite类型，还是任意类型。

texture

导入的图片都视为texture。通过TextureType设置类型。

sprite

TextureType为Sprite(2D and UI)的texture。从U3D4开始出现，作为官方的2D游戏方案。

比普通texture多了边界等可以通过SpriteEditor编辑的属性。sprite一个好用的地方就是，导入一张图集（一个包含很多小图片的大图片），设置SpriteMode为Multiple并在SpriteEditor中切割，就导入所有小图片的sprite了，而且因为只有一张图片所以只有一个DrawCall（Batch），当然内存是没少的，所以图片要小且重复性比较高，不然就亏了。

单个Sprite 直接拖入场景中，系统自动添加SpriteRanderder 组件，作为3D物体直接使用，

多个Sprite（SpriteMode为Multiple的sprite）直接拖入场景，可以直接制作帧动画。

 

说到图集

Unity2017可以生成图集，可参考以下博客

Unity2017新功能Sprite Atlas详解

https://blog.csdn.net/qq826364410/article/details/80979021

 

进一步阅读，可参考：

https://docs.unity3d.com/2017.4/Documentation/Manual/script-Image.html

散图与图集，Image与RawImage，图片的几种格式(Sprite Texture)

https://blog.csdn.net/tran119/article/details/82024848

Sprite 和Texture 的区别

https://blog.csdn.net/july_unity/article/details/79275097#commentBox

Unity中Sprite和UI Image的区别

https://blog.csdn.net/coffeecato/article/details/78536488

Unity中2D和UGUI图集的理解与使用

http://www.cnblogs.com/hammerc/p/4778095.html

To be classified


Breaking the cycle – Colleagues are all you need. https://arxiv.org/abs/1911.10538


EDIT: Exemplar-Domain Aware Image-to-Image Translation. https://arxiv.org/abs/1911.10520


Multi-mapping Image-to-Image Translation via Learning Disentanglement. https://arxiv.org/abs/1909.07877


StarGAN v2: Diverse Image Synthesis for Multiple Domains. https://arxiv.org/abs/1912.01865