Weisheng Dong

Weisheng Dong (董伟生)

Professor

Email: wsdong at mail.xidian.edu.cn

Shot bio: I’m a professor of School of artificial intelligence, Xidian University. I received the Bachlor degree from Huazhong University of Science and Technology (HUST), Wuhan, China, and Ph. D. degree from Xidian University, Xi’an, China. My research interests include low-level vision, inverse problems, computer vision and deep learning. I’m an associate editor of IEEE T-IP and SIAM J. on Imaging Sciences. I’m currently a Chang Jiang Scholar Professor of China Ministry of Education, and a Top-notch Talent Young Scholar of National Ten Thousand Talents Program. I was supported by the Excellent Young Scientist Foundation of NSFC of 2016.

Opening positions:

1) I’m looking for self-motivated Ph. D./M. S. students with solid background in programming and mathematics.

2) I’m also looking for several PostDocs / fresh faculty members with strong research background in computer vision, image processing, and deep learning, to join my group. Please send me email if you have interests.

Home Papers&Codes Links Downloads

Selected publication:

[1] Y. Q. Ning, F. Wu, W. Dong*, X. Li, and G. Shi, “Exploring Correlations in Degraded Spatial Identity Features for Blind Face Restoration,” ACM Multimedia, 2023.

[2] Y. Liu, T. Huang, W. Dong*, X. Li, and G. Shi, “Low-Light image enhancement with multi-stage residue quantization and brightness-aware attention,” IEEE ICCV, 2023. (Paper, project & code)

[3] J. Xu, F. Wu, X. Li, W. Dong, T. Huang, and G. Shi, “Spatially varying prior learning for blind hyperspectral image fusion,” IEEE Trans. on Image Processing, in press, 2023. (Paper, project & code)

[4] T. Huang, W. Dong*, F. Wu, X. Li, and G. Shi, “Uncertainty-driven knowledge distillation for language model compression,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, in press, 2023. (Paper, project & code)

[5] C. Wang, W. Dong*, X. Li, F. Wu, J. Wu, and G. Shi, “Memory based temporal fusion network for video deblurring,” International Journal of Computer Vision, 2023. (Paper, project & code)

[6] T. Huang, X. Yuan, W. Dong*, J. Wu, and G. Shi, “Deep Gaussian Scale Mixture Prior for Image Reconstruction,” IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI), 2023. (Paper, project & code)

[7] Z. Yang, W. Dong*, X. Li, Y. Sun, M. Huang and G. Shi, “Vector Quantization with Self-attention for Quality-independent Representation Learning”, IEEE CVPR 2023. (Paper, project & code)

[8] Z. Fang, F. Wu, W. Dong, X. Li, J. Wu and G. Shi, “Self-supervised non-uniform kernel estimation with flow-based motion prior for blind image deblurring,” IEEE CVPR 2023. (Paper, project & code)

[9] Chengxing Xie, Qian Ning, Weisheng Dong, Guangming Shi, “TFRGAN: Leveraging Text Information for Blind Face Restoration with Extreme Degradation”, CVPR Workshops, pp. 2535-2545, 2023.

[10] X. Lu, W. Dong*, X. Li, J. Wu, L. Li, and G. Shi, “Adaptive search-and-training for robust and efficient network pruning,” IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI), 2023. (Paper, project & code)

[11] Xin Li, Weisheng Dong, Jinjian Wu, Leida Li, Guangming Shi, “Super-resolution Image Reconstruction: Selective milestones and open problems”, IEEE Signal Process. Mag., vol. 40, no. 5, pp. 54-66, 2023.

[12] L. Sun, Y. Wang, F. Wu, X. Li, W. Dong, and G. Shi, “Deep unfolding network for efficient mixed video noise removal,” IEEE Trans. on Circuits and System for Video Technology (T-CSVT), 2023. (Paper, project & code)

[13] Q. Ning, W. Dong*, X. Li and J. Wu, “Searching efficient model-guided deep network for image denoising,” IEEE Trans. on Image Processing, vol. 23, pp. 668-681, 2023. (Paper, project & code).

[14] Han Huang, Li Shen, Chaoyang He, Weisheng Dong, Wei Liu, “Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution”, IEEE Trans. Circuits Syst. Video Technol., vol. 33, no. 6, pp. 2672-2682, 2023.

[15] Mengluan Huang, Le Dong, Weisheng Dong, Guangming Shi, “Supervised Contrastive Learning Based on Fusion of Global and Local Features for Remote Sensing Image Retrieval”, IEEE Trans. Geosci. Remote. Sens., vol. 61, pp. 1-13, 2023.

[16] Z. Fang, W. Dong*, X. Li, J. Wu, L. Li, and G. Shi, “Uncertainty learning in kernel estimation for multi-stage blind image super-resolution,” ECCV 2022. (Paper, project & code) (A novel kernel estimation method was proposed with uncertainty learning, achieving SOTA blind image SR results.)

[17] Z. Yang, W. Dong*, X. Li, J. Wu, L. Li, and G. Shi, “Self-feature distillation with uncertainty modeling for degraded image recognition,” ECCV 2022. (Paper, project & code) (A weighted feature distillation loss with uncertainty learning was proposed for degraded image recognition.)

[18] X. Lu, T. Xi, B. Li, G. Zhang, and W. Dong, “Bayesian based re-parameterization for DNN model pruning,” ACM Multimedia, 2022. (Paper)

[19] W. Dong, J. Wu, L. Li, G. Shi, and X. Li, “Bayesian deep learning for image reconstruction: from structured sparsity to uncertainty estimation,” IEEE Signal Processing Magazine, vol. 40, no. 1, pp. 73-84, 2023. (Paper)

[20] Q. Ning, J. Tang, F. Wu, W. Dong*, et al., “Learning degradation Uncertainty for unsupervised real-world image super-resolution,” IJCAI 2022. (Paper, project & code) (Uncertainty-based loss for simulating real LR images for unsupervised real image SR.)

[21] T. Huang, W. Dong*, J. Wu, L. Li, X. Li, and Guangming Shi, “Deep hyperspectral image fusion network with iterative spatio-spectral regularization,” IEEE Trans. on Computational Imaging, in press, 2022. (Paper, project & code)

[22] Y. Zhu, W. Dong*, X Li, J. Wu, L. Li, and G. Shi, “Robust depth completion with uncertainty-driven loss functions,” AAAI 2022. (Paper, project & code)

[23] Q. Ning, W. Dong*, X. Li, J. Wu, and G. Shi, “Uncertainty-driven loss for single image super-resolution,” NeurIPS 2021. (Paper, project & code)

[24] Y. Cao, G. Shi, T. Zhang, W. Dong*, J. Wu, X. Xie, and X. Li, “Bayesian correlation filter learning with Gaussian scale mixture model for visual tracking”, IEEE Trans. on Circuit and Systems for Video Technology (T-CSVT), 2021. (Paper, Project & Code)

[25] L. Sun, W. Dong*, X. Li, J. Wu, L. Li, and G. Shi, “Deep maximum a posterior estimator for video denoising”, International Journal of Computer Vision (IJCV), accepted, 2021. (Paper, Project & Code) (MAP-based video denoising algorithm was unfolded into a deep network, leading to principle and state-of-the-art video denoising performance!)

[26] W. Dong, C. Zhou, F. Wu, J. Wu, G. Shi, and X. Li, “Model-guided deep hyperspectral image super-resolution,” IEEE Trans. on Image Processing (T-IP), 2021. (Paper, Project & Code) (A model-guided DCNN was proposed for hyperspectral image super-resolution, obtaining state-of-the-art performance!)

[27] T. Huang, W. Dong*, X. Yuan*, J. Wu, and G. Shi, “Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging,” IEEE CVPR 2021. (Paper, Project & Code) (Deep Gaussian Scale Mixture network was proposed to learn the parametric image distributions, leading to state-of-the-art Spectral image reconstruction performance!)

[28] Q. Ning, W. Dong*, G. Shi, L. Li and X. Li, “Accurate and lightweight image super-resolution with model-guided deep unfolding network,” IEEE Journal of Selected Topics on Signal Processing (J-STSP), vol. 15, no. 2, pp. 240-252, Feb. 2021. (Paper, Code, Github) (A deep nonlocal auto-regressive model is imbedded into the network obtaining state-of-the-art image SR performance!)

[29] X. Lu, H. Huang, W. Dong*, G. Shi, and X. Li, “Beyond network pruning: a joint search-and-training approach,” IJCAI, 2020. (Paper, 12% acceptance rate！Project, Code.)

[30] T. Huang, W. Dong*, J. Liu, F. Wu, G. Shi, and X. Li, “Accelerating convolutional neural network via structured Gaussian scale mixture models: a joint grouping and pruning approach,” IEEE Journal of Selected Topics on Signal Processing (J-STSP), vol. 14, no. 4, pp. 817-827, May, 2020. (Paper, Code)

[31] Q. Ning, W. Dong*, F. Wu, J. Wu, J. Lin, and G. Shi, “Spatial-temporal Gaussian scale mixture modeling for foreground estimation,” AAAI 2020. (Paper, code coming soon)

[32] W. Dong, H. Wang, F. Wu, G. Shi, and X. Li, “Deep spatial-spectral representation learning for hyperspectral image denoising”, IEEE Trans. on Computational Imaging (T-CI), vol. 5, no. 4, pp. 635-648, 2019. (Paper, code)

[33] Weisheng Dong*, P. Wang, W. Yin, G. Shi, F. Wu, and X. Lu, “Denoising Prior Driven Deep Neural Network for Image Restoration” IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI), Vol. 41, no. 10, pp. 2308-2318, Oct., 2019. (Paper) (Code)

[34] Y. Li, Weisheng Dong*, X. Xie, G. Shi, J. Wu, and X. Li, “Image Super-resolution with Parametric Sparse Model Learning”, IEEE Trans. on Image Processing (T-IP), vol. 27, no. 9, pp. 4638-4650, Sep., 2018. (Paper)

[35] G. Shi, T. Huang, Weisheng Dong*, J. Wu, and X. Xie, “Robust Foreground Estimation via Structured Gaussian Scale Mixture Modeling”, IEEE Trans. on Image Processing (T-IP), vol. 27, no. 10, pp. 4810-4824, 2018. (Paper) (Code) (A principled foreground estimation method with very effective performance!)

[36] Weisheng Dong, T. Huang, G. Shi, Y. Ma, and X. Li, “Robust tensor approximation with Laplacian scale mixture modeling for multiframe image and video denoising,” IEEE Journal of Selected Topics on Signal Processing (J-STSP), vol. 12, no. 6, Dec. 2018. (Paper) (Code)

[37] Tao Huang, Weisheng Dong*, Xuemei Xie, Guangming Shi, and Xiang Bai, “Mixed noise removal via Laplacian scale mixture modeling and nonlocal low-rank approximation,” IEEE Trans. on Image Processing (T-IP), 2017. (Paper, Code) (State-of-the-art mixed noise removal algorithm!)

[38] Weisheng Dong, Guangming Shi, Xin Li, K. Peng, J. Wu, and Z. Guo, “Color-guided depth recovery via joint local structural and nonlocal low-rank regularization,” IEEE Trans. on Multimedia, vol. 19, no. 2, pp. 293-301, Feb. 2017. (Paper, Code)

[39] Y. Li, W. Dong*, X. Xie, G. Shi, X. Li, and D. Xu, "Learning parametric sparse models for image super-resolution," NIPS, 2016. (Paper)

[40] Weisheng Dong, Fazuo Fu, Guangming Shi, and Xun Cao, Jinjian Wu, Guangyu Li, and Xin Li, “Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation”, IEEE Trans. On Image Processing, vol. 25, no. 5, pp. 2337-2352, May 2016. (Paper, Project, Code) (A very effective non-negative dictionary learning and sparse coding algorithm has been proposed!)

[41] W. Dong, G. Shi, Y. Ma, and X. Li, “Image Restoration via Simultaneous Sparse Coding: Where Structured Sparsity Meets Gaussian Scale Mixture,” International Journal of Computer Vision (IJCV), vol. 114, no. 2, pp. 217-232, Sep. 2015. (Paper) (Denoising Code) (State-of-the-art Image Restoration performance!).

[42] Weisheng Dong, Guangyu Li, Guangming Shi, Xin Li, and Yi Ma, "Low-rank tensor approximation with Laplacian scale mixture modeling for multiframe image denoising", in Proc. IEEE Int. Conf. on Computer Vision (ICCV), 2015. (PDF)

[43] Yongbo Li, Weisheng Dong*, Guangming Shi, and Xuemei Xie, "Learning parametric distributions for image super-resolution: where patch matching meets sparse coding," in Proc. IEEE Int. Conf. on Computer Vision (ICCV), 2015. (PDF)

[44] W. Dong, G. Shi, X. Li, Y. Ma, and F. Huang, “Compressive sensing via nonlocal low-rank regularization”, IEEE Trans. on Image Processing, vol. 23, no. 8, pp. 3618-3632, 2014. (Paper) (Project&Code) (State-of-the-art CS reconstruction performance on both natural images and complex-valued MRI images!)

My Google Scholar Citation profile: http://scholar.google.com/citations?user=-g58LsoAAAAJ&hl=en

Last update: May. 9, 2021.