Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Yunjin Chen

Learning Generic Diffusion Processes for Image Restoration

Jul 17, 2018
Peng Qiao, Yong Dou, Yunjin Chen, Wensen Feng

* British Machine Vision Conference 2018 
* 12 pages, 3 figures, 3 tables 

  Access Paper or Ask Questions

LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT

Feb 10, 2018
Hu Chen, Yi Zhang, Yunjin Chen, Junfeng Zhang, Weihua Zhang, Huaiqiaing Sun, Yang Lv, Peixi Liao, Jiliu Zhou, Ge Wang

* 18 pages, 15 figures, accepted by IEEE TMI 

  Access Paper or Ask Questions

Speckle Reduction with Trained Nonlinear Diffusion Filtering

Feb 24, 2017
Wensen Feng, Yunjin Chen

* to appear in Journal of Mathematical Imaging and Vision. Demo codes are available from!ApXF85Oq1kvqgcscP8GqUvPE-dF7ig 

  Access Paper or Ask Questions

Learning Non-local Image Diffusion for Image Denoising

Feb 24, 2017
Peng Qiao, Yong Dou, Wensen Feng, Yunjin Chen

* under review in a journal 

  Access Paper or Ask Questions

Image Denoising via Multi-scale Nonlinear Diffusion Models

Sep 21, 2016
Wensen Feng, Peng Qiao, Xuanyang Xi, Yunjin Chen

  Access Paper or Ask Questions

Poisson Noise Reduction with Higher-order Natural Image Prior Model

Sep 19, 2016
Wensen Feng, Hong Qiao, Yunjin Chen

* 31 pages, 10 figures. To appear in SIAM Journal on Imaging Sciences 

  Access Paper or Ask Questions

Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration

Aug 20, 2016
Yunjin Chen, Thomas Pock

* 14 pages, 13 figures, to appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 

  Access Paper or Ask Questions

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Aug 13, 2016
Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang

  Access Paper or Ask Questions

Higher-order MRFs based image super resolution: why not MAP?

Oct 24, 2015
Yunjin Chen

* 16 pages, 5 figures 

  Access Paper or Ask Questions

Fast and Accurate Poisson Denoising with Optimized Nonlinear Diffusion

Oct 10, 2015
Wensen Feng, Yunjin Chen

* 11 pages, 12 figures, technical report 

  Access Paper or Ask Questions

On learning optimized reaction diffusion processes for effective image restoration

Mar 25, 2015
Yunjin Chen, Wei Yu, Thomas Pock

* 9 pages, 3 figures, 3 tables. CVPR2015 oral presentation together with the supplemental material of 13 pages, 8 pages (Notes on diffusion networks) 

  Access Paper or Ask Questions

A higher-order MRF based variational model for multiplicative noise reduction

Jul 07, 2014
Yunjin Chen, Wensen Feng, René Ranftl, Hong Qiao, Thomas Pock

* 5 pages, 5 figures, to appear in IEEE Signal Processing Letters 

  Access Paper or Ask Questions

A bi-level view of inpainting - based image compression

May 09, 2014
Yunjin Chen, René Ranftl, Thomas Pock

* 8 pages, 4 figures, best paper award of CVWW 2014, Computer Vision Winter Workshop, K\v{r}tiny, Czech Republic, 3-5th February 2014 

  Access Paper or Ask Questions

iPiano: Inertial Proximal Algorithm for Non-Convex Optimization

Apr 18, 2014
Peter Ochs, Yunjin Chen, Thomas Brox, Thomas Pock

* 32pages, 7 figures, to appear in SIAM Journal on Imaging Sciences 

  Access Paper or Ask Questions

Revisiting loss-specific training of filter-based MRFs for image restoration

Jan 16, 2014
Yunjin Chen, Thomas Pock, René Ranftl, Horst Bischof

* 10 pages, 2 figures, appear at 35th German Conference, GCPR 2013, Saarbr\"ucken, Germany, September 3-6, 2013. Proceedings 

  Access Paper or Ask Questions

Learning $\ell_1$-based analysis and synthesis sparsity priors using bi-level optimization

Jan 16, 2014
Yunjin Chen, Thomas Pock, Horst Bischof

* 5 pages, 1 figure, appear at the Workshop on Analysis Operator Learning vs. Dictionary Learning, NIPS 2012 

  Access Paper or Ask Questions

Insights into analysis operator learning: From patch-based sparse models to higher-order MRFs

Jan 13, 2014
Yunjin Chen, René Ranftl, Thomas Pock

* 13 pages, 10 figures, accepted to IEEE Image Processing 

  Access Paper or Ask Questions