Welcome to Feng Xue’s Homepage.

Dr. Feng Xue is a senior engineer of National Key Laboratory of Science and Technology on Test Physics and Numerical Mathematics, Beijing, 100076, China.

Short Bio

I received the B.Eng. and M.Eng. from Harbin Institute of Technology, Harbin, China, and the Ph.D. degree in electronics engineering from the Chinese University of Hong Kong (CUHK), Shatin, Hong Kong, in 2013, under the supervision of Prof. Thierry Blu. I am currently with the National Key Laboratory of Science and Technology on Test Physics and Numerical Mathematics, Beijing, 100076, China. My research interests include unbiased risk estimation, convex analysis and variational methods with applications to imaging problems.

If you have any problems with my research works, please contact me by email: fxue (at) hotmail (dot) com.

Languages

Chinese, Russian, English

Research areas

Image deconvolution, sparse signal reconstruction, unbiased risk estimation, numerical optimization.

Research projects

• Performance analysis of electro-optical imaging system (Sep. 2005 – Jul. 2007)
• The sub-pixel imaging process in point-target detection (Sep. 2007 – Jul. 2009)
• Mathematical modelling of point spread function of fluorescence microscopy (Jul. 2009 - Feb. 2010)
• Multi-Wiener SURE-LET approach to non-blind deconvolution (Feb. 2010 – Apr. 2012)
• SURE-based approach to parametric blind deconvolution (Nov. 2011 – Jul. 2015)
• Recursive evaluation of SURE for sparse signal reconstruction (Jun. 2015 – Jul. 2018)
• Theoretical analysis of degrees of freedom in SURE (Jul. 2018 – )
• Convergence analysis of first-order optimization algorithms from proximal point perspective (Jul. 2019 – )

Funding

• Unbiased risk estimate algorithms for blind image deconvolution: NSFC #61401013, CNY 290’000, Jan. 2015 — Dec. 2017.

Academic activities

• Reviewer to Journals: SIAM J. Imaging Sciences, IEEE Signal Processing Magazine, IEEE TIP, EURASIP Journal on image and video processing, Signal, image and video processing, International Journal of Computer Assisted Radiology and Surgery, Applied Optics.

Ph.D thesis

Unbiased risk estimate algorithms for image deconvolution. The Chinese University of Hong Kong, June, 2013.

Journal articles

• Feng Xue, Jiaqi Liu and Xia Ai. Parametric PSF Estimation based on predicted-SURE with l1-penalized sparse deconvolution. Signal, Image and Video Processing, vol. 13, no. 4, 2019, pp. 635–642. [pdf]
• Feng Xue, Jiaqi Liu and Xia Ai. Recursive SURE for image recovery via total variation minimization. Signal, Image and Video Processing, vol. 13, no. 4, 2019, pp. 795–803. [pdf]
• Jizhou Li, Feng Xue, Fuyang Qu, Yiping Ho and Thierry Blu. On-the-fly estimation of a microscopy point spread function. Optics Express, vol. 26, no. 20, 2018, pp. 26120–26133. [pdf]
• Jizhou Li, Feng Xue, Thierry Blu. Fast and accurate 3D PSF computation for fluorescence microscopy. Journal of the Optical Society of America A, vol. 34, no. 6, 2017, pp. 1029–1034. [pdf]
• Feng Xue, Anatoly G. Yagola, Jiaqi Liu and Gang Meng. Recursive SURE for iterative reweighted least square algorithms. Inverse Problems in Science and Engineering, vol. 24, no. 4, 2016, pp. 625–646. [pdf]
• Feng Xue, Jiaqi Liu, Shenghai Jiao, Shengdong Liu, Min Zhao and Zhenhong Niu. SURE- type functionals as criteria for parametric PSF estimation. Journal of Mathematical Imaging and Vision, vol. 54, no. 1, 2016, pp. 78–105. [pdf]
• Feng Xue, Jiaqi Liu, Zhifeng Li, Shengdong Liu, Gang Meng and Li Zhang. Mallows’ statistics CL: a novel criterion for parametric PSF estimation. Journal of Visual Communication and Image Representation, vol. 33, pp. 115–122, Nov. 2015.
• Feng Xue and Thierry Blu. A novel SURE-based criterion for parametric PSF estimation. IEEE Transactions on Image Processing, vol. 24, no. 2, 2015, pp. 595–607. [pdf]
• Feng Xue, Florian Luisier and Thierry Blu. Multi-Wiener SURE-LET deconvolution. IEEE Transactions on Image Processing, vol. 22, no. 5, 2013, pp. 1954–1968. [pdf]
• Feng Xue and Anatoly Yagola. Analysis of point-target detection performance based on ATF and TSF. Infrared Physics & Technology, vol. 52, no. 5, pp. 166–173, Sep. 2009. [pdf]

Conference papers

• Feng Xue and Thierry Blu. On the degrees of freedom in total variation minimization. In Proc. of the 45th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, May 4–8, 2020, to appear.
• Feng Xue, Jizhou Li and Thierry Blu. An iterative SURE-LET deconvolution algorithm based on BM3D denoiser. In Proc. of the IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, September 22–25, 2019, pp. 1795–1799.
• Feng Xue, Thierry Blu, Jiaqi Liu and Xia Ai. A novel GCV-based criterion for parameter selection in image deconvolution. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, April 15–20, 2018, pp. 1403–1407. [pdf]
• Feng Xue, Thierry Blu, Jiaqi Liu and Xia Ai. Recursive evaluation of SURE for total variation denoising. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, April 15–20, 2018, pp. 1338–1342. [pdf]
• Jizhou Li, Feng Xue and Thierry Blu. Accurate 3D PSF estimation from a wide-field microscopy image. In Proc. of the IEEE International Symposium on Biomedical Imaging (ISBI), Washington, D.C., USA, April 04–07, 2018, pp. 501–504. [pdf]
• Jizhou Li, Feng Xue, Thierry Blu. Gaussian blur estimation for photon-limited images. In Proc. of the IEEE International Conference on Image Processing (ICIP), Beijing, China, September 17–20, 2017, pp. 495–499. [pdf]
• Feng Xue, Lian Xue and Jiaqi Liu. A family of risk estimators as criteria for PSF estimtion: from SURE to GCV. In Proc. of the IEEE International Conference on Image Processing (ICIP), Beijing, China, September 17–20, 2017, pp. 2428–2432. [pdf]
• Feng Xue, Hanjie Pan, Xin Liu, Hongyan Liu and Jiaqi Liu. Optimization of regularization parameter for sparse reconstruction based on predictive risk estimate. In Proc. of the IEEE International Conference on Image Processing (ICIP), Beijing, China, September 17–20, 2017, pp. 1442–1446. [pdf]
• Feng Xue, Hanjie Pan, Runhui Wu, Xin Liu and Jiaqi Liu. Optimization of compound regularization parameters based on Stein’s unbiased risk estimate. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, USA, March 05–09, 2017, pp. 4591–4595. [pdf]
• Feng Xue, Thierry Blu, Runle Du and Jiaqi Liu. An iterative SURE-LET approach to sparse reconstruction. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, March 20–25, 2016, pp. 4493–4497. [pdf]
• Feng Xue, Runle Du and Jiaqi Liu. A recursive predictive risk estimate for proximal algorithms. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, March 20–25, 2016, pp. 4498–4502. [pdf]
• Feng Xue, Jiaqi Liu, Zhifeng Li and Gang Meng. A novel GCV-based criterion for parametric PSF estimation. In Proc. of the IEEE International Conference on Signal Processing (ICSP), Hangzhou, China, October 19–23, 2014, pp. 743–746. [pdf]
• Feng Xue, Jiaqi Liu, Chengguo Liu and Gang Meng. A blur-SURE-LET algorithm to blind PSF estimation for deconvolution. In Proc. of the IEEE International Conference on Signal Processing, Communications & Computing (ICSPCC), Guilin, China, August 05–08, 2014, pp. 98–101. [pdf]
• Feng Xue, Florian Luisier and Thierry Blu. SURE-LET image deconvolution using multiple Wiener filters. In Proc. of the IEEE International Conference on Image Processing (ICIP), Orlando, Florida, USA, September 30–October 03, 2012, pp. 3037–3040. [pdf]
• Feng Xue and Thierry Blu. SURE-based motion blur estimation. In Proc. of the IEEE International Conference on Signal Processing, Communications & Computing (ICSPCC), Hong Kong, August 12–15, 2012, pp. 373–377. [pdf]
• Feng Xue and Thierry Blu. SURE-based blind Gaussian deconvolution. In Proc. of the IEEE Statistical Signal Processing Workshop (SSP), Ann Arbor, USA, August 05–08, 2012, pp. 452–455. [pdf]