zdlarr / location-aware-sirr Goto Github PK
View Code? Open in Web Editor NEWCode for the paper "Location-aware Single Image Reflection Removal"
Home Page: https://arxiv.org/abs/2012.07131
Code for the paper "Location-aware Single Image Reflection Removal"
Home Page: https://arxiv.org/abs/2012.07131
Hello, teacher. I downloaded the code and model you provided on the Internet pth。 I want to reproduce the teacher's experiment first, but I'm running information There are the following errors in py (with photos). Do you know the reason, teacher? Thank the teacher for taking time out of his busy schedule to answer the students. Thank you very much!!
您的github只提供了测试的代码,请问能提供训练的代码吗?
一直在关注您的这项工作,去反光效果惊人,什么时候能开源训练代码让小弟学习一下,期待您的回复。
Hello, teacher, The results of your experiment are very impressive on real world dataset. I would like to reproduce the training process to have further research.But there is only evaluation code in github, could you provide the training source code? Thank you so much!
We noticed that you mentioned the setting of training data in the fifth part of your paper.
“For the synthetic data, we use the images dataset from [4]. This dataset has approximately 13700 image pairs of size 256 × 256”.
However, in paper 4(A generic deep architecture for single image reflection removal and image smoothing), about 8k images can be synthesized according to its method, which is not 13700 you mentioned.
In fact, I found the meaning of 13700 in the data set used in the work of "Single Image Reflection Removal with Perceptual Losses".
But I don't know if this is the training dataset you really use. This caused me great confusion.
I would appreciate it if you could answer the question about the source of the composite dataset when you have time!
And it would be better if you could provide the code of data synthesis by the way or indicate which method of data synthesis is most similar to that of the work!
Thank you for your wonderful work!
Hello, teacher, The results of your experiment are very impressive on real world dataset. I would like to reproduce the training process to have further research.But there is only evaluation code in github, could you provide the training source code? Thank you so much!
hello, can you tell me where the result that have removed the reflaction
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.