Comments (16)
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.
Please check the following nice post:
https://stackoverflow.com/questions/26812289/matlab-vs-c-vs-opencv-imresize
from edsr-pytorch.
thank you very much. i have solved this problem when i used your suggest.
from edsr-pytorch.
@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.
@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.
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.
@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.
不是
from edsr-pytorch.
@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.
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.
@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
from edsr-pytorch.
@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.
@ShiinaMitsuki
GT(LR):1920*1080
from edsr-pytorch.
@ShiinaMitsuki , 如果原图就很糟糕,放大后别指望多好
from edsr-pytorch.
@thstkdgus35 I can't understand. can you explain more how we can use it for other images??
from edsr-pytorch.
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)
- About eval
- About test HOT 3
- train和test中的指标不同
- PSNR is nan when test DIV2K data HOT 2
- Why does EDSR enlarge the image twice and only low pixel images work well? HOT 3
- Mean Shift Function for Gray Image dataset
- TypeError:list indices must be integers or slices, not tuple
- transfer learning / finetune HOT 1
- Why not use torchvision.transforms HOT 1
- where's baseline models? HOT 1
- PSNR and SSIM
- It is not working Correctly!
- ValueError: num_samples should be a positive integer value, but got num_samples=0 HOT 4
- ValueError: x and y must have same first dimension, but have shapes (0,) and (1,)
- Denoising model in "Residual Dense Network for Image Restoration"
- Not changing the speed by changing the amount of data
- 环境配置 HOT 4
- AttributeError: module 'torch.backends' has no attribute 'mps' HOT 1
- 训练数据集
- 怎么使用自定义的数据集训练? HOT 10
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from edsr-pytorch.