Comments (8)
I think you are missing the essence and you should re-read the paper.
in short:
We first generate the dataset with randomly generate kernels (AKA GT kernel).
Then apply one GT kernel for each HR image and obtain LR images.
We then apply kernel-GAN to estimate that GT kernel, but note that all the GAN sees in the LR image.
The generation of the dataset can be found here:
https://github.com/assafshocher/BlindSR_dataset_generator
The GT kernel's are generated randomly so each image is then downscaled with a different kernel.
from kernelgan.
I don't understand.
This repo is exactly the open-source code
from kernelgan.
AFAIK Michaeli & Irani didn't publish their code. I got Irani's lab to run the kernel estimation on the DIV2KRK dataset that you see in the figures
from kernelgan.
How is the Ground-truth kernel obtained ,the second row in Figure 5 and the first row in Figure 6
from kernelgan.
It is randomly generated, then we downscale a HR image to obtain the LR version.
The details can be found in chapter 5.2 of the paper
from kernelgan.
and what does the "Convolving all filters of G results with the SR Kernel K" means? The "K" is the Ground-truth kernel? K is another input of Generator?
from kernelgan.
The whole essence of the work is to estimate K. it is not given as input.
I recommend reading the paper
from kernelgan.
It is randomly generated, then we downscale a HR image to obtain the LR version. The details can be found in chapter 5.2 of the paper
Could you tell me the specific operation? ”randomly generated“ means kernel estimation of GT image?if not, how to randomly generated and visualization?Is there a open code?
from kernelgan.
Related Issues (20)
- X4 kernel specs in DIV2KRK HOT 1
- It seems like a bug?
- UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize HOT 5
- RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM HOT 2
- network parameter asking HOT 6
- Why do you swap axis? HOT 2
- why not directly save the params of Generator for downscaling? why not non-linear? HOT 3
- Question about the DownScaleLoss HOT 1
- About DIV2KRK HOT 1
- about Generator and Discriminator output size HOT 5
- Questions about generator networks HOT 2
- How do you visualize the ".mat" files HOT 3
- There was a problem with training in another data set HOT 1
- How to gain the PSNR and SSIM HOT 2
- What's the meaning of "input-dir" and "input_img_path"
- Is your training data set the same as your test set HOT 2
- Why there needs flip orperation when calculate the kernel ? HOT 1
- No file .mat HOT 1
- ValueError: shapes (512,512,1) and (3,) not aligned: 1 (dim 2) != 3 (dim 0) HOT 2
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 kernelgan.