subeeshvasu / awesome-deblurring Goto Github PK
View Code? Open in Web Editor NEWA curated list of resources for Image and Video Deblurring
A curated list of resources for Image and Video Deblurring
Hello There, can you please add this paper to this repository:
Thank you!
Sorry, the paper link to our project is wrong.
(Multi-image/Video)-Motion-Deblurring:
Spatio-Temporal Efficient Recurrent Neural Network for Video Deblurring (ECCV 2020)
The correct one is:
Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring
https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/5116_ECCV_2020_paper.php
And the code is available now as follows:
https://github.com/zzh-tech/ESTRNN
https://arxiv.org/abs/2208.09483
thanks for maintaining the excellent resource as well!
Hi,
Thanks for your list.
Could you add the official code for the paper "Explore image deblurring via encoded blur kernel space"?
Here is the code: https://github.com/VinAIResearch/blur-kernel-space-exploring
Thanks.
Hello,
You might consider adding pmapper, an implementation of PMAP we have created at JPL. A relevant citation would be Multiframe Restoration Methods for Image Synthesis and Recovery, Joseph J. Green, Univ. of Arizona, PhD thesis
Cheers
-Brandon
@subeeshvasu This is a very useful list.
I would like to propose two additions, if you allow me:
They would belong to the category 'non-blind' (strictly speaking 'semi-blind'). These are non-DL methods.
Paper Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels / DPSR is non-blind model-based SISR method which assumes the blur kernel is known.
Could you please help us add the code link to this paper :
Motion Deblur with real events, ICCV 2021.
https://github.com/xufangchn/Motion-Deblurring-with-Real-Events
Thanks.
Lei
Hello!
Was looking around for latest gyro-assisted denoising methods, and found two new papers from this year which I think would fit well on this list.
Gyro-based Neural Single Image Deblurring
Heemin Yang, Jaesung Rim, Seungyong Lee, Seung-Hwan Baek, Sunghyun Cho
https://arxiv.org/abs/2404.00916
Gyroscope-Assisted Motion Deblurring Network
Simin Luan, Cong Yang, Zeyd Boukhers, Xue Qin, Dongfeng Cheng, Wei Sui, Zhijun Li
https://arxiv.org/abs/2402.06854
Thanks a lot for maintaining these great lists! Super useful :)
Cheers
I would like to propose one additions, if you allow me:
Could you add a reference to this list?
"Fast non-blind deconvolution via regularized residual networks with long/short skip-connections" by Son and Lee (in ICCP 2017).
Project page: http://cg.postech.ac.kr/research/resnet_deconvolution/
Thank you for the nice list
The paper ‘‘Convolutional neural networks for direct text deblurring ’’ and ''Blind image deconvolution using deep generative priors'' were accepted by bmvc'15 and bmvc'19 respectively.
see:
http://www.bmva.org/bmvc/2015/papers/paper006/index.html
https://bmvc2019.org/wp-content/uploads/papers/1042-paper.pdf
You could add one more reference to this list:
MRF-based blind image deconvolution by Komodakis and Paragios
Link: http://imagine.enpc.fr/~komodakn/publications/docs/accv2012.pdf
Nice list! Thank you.
Hello, thank you for the awesome list!
Can you please add these two references to the list?
The codes will be released soon (I will ask for an update later).
[1] Motion-blurred Video Interpolation and Extrapolation (AAAI 2021)
https://arxiv.org/pdf/2103.02984.pdf
[2] Optical Flow Estimation from a Single Motion-blurred Image (AAAI 2021)
https://arxiv.org/pdf/2103.02996.pdf
Thanks a lot in advance :)
Hi Vasu, please help to change the following publications accordingly.
(1) For "Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring", please change the paper link to "https://github.com/ysnan/VEM-NBD/blob/master/paper/vem_deconv.pdf" as this is the newest version and add the project page with link "https://github.com/ysnan/VEM-NBD"
(2) For "Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution", please change the paper link to “https://github.com/ysnan/NBD_KerUnc/blob/master/paper/kn.pdf” and add the project page with link "https://github.com/ysnan/NBD_KerUnc"
I would also like to express my gratitude for setting up and maintaining this page for the collection of deblurring papers. It helps me a lot.
Please use the proper -
or +
or *
instead for better Markdown
Is there any paper talking about RAW image/video deblurring? Thanks (RAM image instead of RGB image).
Hi, thank you so much for the awesome summary!
We have upgraded and released the real video deblurring dataset BSD (more blur intensity and motion pattern settings, and better design of beam-splitter acquisition system).
So, could you please also put the following item:
2020 | ECCV | Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring | Code |
---|
in the following field:
Benchmark Datasets on Motion Deblurring
Thank you :)
Hello, first of all, thank you for your efforts to collect and integrate resources. Will the latest articles on non-DL and DL image deblurring be updated?
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.