Giter VIP home page Giter VIP logo

Comments (16)

sanghyun-son avatar sanghyun-son commented on July 29, 2024 4

Hello.

It seems that your input image is not downsampled by bicubic interpolation method. (I guess you used nearest-neighbor, since there are many aliasing artifacts.)

Since our model mainly handles bicubic-downsampled input images, we cannot guarantee the super-resolution result from your input. (It seems weird, I know. This situation is a common problem in recent deep super-resolution models.)

If you are trying to apply our method to that kind of images, I recommend you to train (or fine-tune) our model with nearest-neighbor downsampling method.

Thank you.

from edsr-pytorch.

yu4u avatar yu4u commented on July 29, 2024 1

Please check the following nice post:
https://stackoverflow.com/questions/26812289/matlab-vs-c-vs-opencv-imresize

from edsr-pytorch.

stojakovic312636841 avatar stojakovic312636841 commented on July 29, 2024

thank you very much. i have solved this problem when i used your suggest.

from edsr-pytorch.

suke27 avatar suke27 commented on July 29, 2024

@thstkdgus35 do you mean EDSR is just suit for bicubic downsampleed images, if we get a input images, we can not know whether it is downsample or just noise images

from edsr-pytorch.

stojakovic312636841 avatar stojakovic312636841 commented on July 29, 2024

@suke27
个人认为EDSR的input和target之间是bicubicu的放大关系,因此EDSR学习的就是bicubic放大功能。
在running的时候,input任何形式的图片都可以,input的图片通过EDSR之后,等效bicubic放大。

而我出现的问题在于,我将原始图片target,没有通过bicubic方式缩小成input。而后,将input通过EDSR后得到的output与target进行对比。此时的target != output 是合理的

from edsr-pytorch.

suke27 avatar suke27 commented on July 29, 2024

只有bicubic 方式缩写的input 放大才会有比较好的效果, 是这个意思么,如果通过其他方式(压缩降质) 之类的就会效果很差?

from edsr-pytorch.

stojakovic312636841 avatar stojakovic312636841 commented on July 29, 2024

@suke27
你可以随便使用自己的原始图片(从网络上随便找)不通过bicubic缩小,直接进行EDSR,看一看效果。

from edsr-pytorch.

suke27 avatar suke27 commented on July 29, 2024

不是

from edsr-pytorch.

splinter21 avatar splinter21 commented on July 29, 2024

@stojakovic312636841 所以你试过用预训练的EDSR模型继续用非双立方缩小的input-GT pairs,训练出针对不同缩小方式的模型吗,这种思路是否可行,还是说EDSR这种结构就只能训练双立方缩小的input-GT pairs

from edsr-pytorch.

splinter21 avatar splinter21 commented on July 29, 2024

或者基于预训练的ESDR模型,喂各种缩小方法的input-GT pairs,可能双立方测试跑分会下降,但是可以或多或少学习到各种缩小方式的超分重建?

from edsr-pytorch.

stojakovic312636841 avatar stojakovic312636841 commented on July 29, 2024

@splinter22
我想你应该阅读一下这篇简报《Ntire 2017 challenge on single image superresolution_ Methods and results-CVPRW-2017》,明确说明了如何比赛。EDSR总共训练了6个模型,3个模型参加bicubic downscaling。又有3个模型参加unknown downscaling
http://www.vision.ee.ethz.ch/~timofter/publications/Timofte-CVPRW-2017.pdf

image

from edsr-pytorch.

ShiinaMitsuki avatar ShiinaMitsuki commented on July 29, 2024

@suke27 你好,请问你试过直接将原始低分辨率的图片作为input然后用网络进行放大吗?我这边测试发现效果很不好。

from edsr-pytorch.

stojakovic312636841 avatar stojakovic312636841 commented on July 29, 2024

@ShiinaMitsuki
GT(LR):1920*1080
gt_020

SR:7680*4320
tfx4

from edsr-pytorch.

suke27 avatar suke27 commented on July 29, 2024

@ShiinaMitsuki , 如果原图就很糟糕,放大后别指望多好

from edsr-pytorch.

 avatar commented on July 29, 2024

@thstkdgus35 I can't understand. can you explain more how we can use it for other images??

from edsr-pytorch.

HuangBiaoVivo avatar HuangBiaoVivo commented on July 29, 2024

你好,如果我用大赛第二赛道的图片进行ESDR训练,得出的模型能否有效消除输入图片的一些噪声和模糊呢?

from edsr-pytorch.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.