Publications

Preprints

Cross-scale self-supervised blind image deblurring via implicit neural representation
T. Zhang, Y. Quan, and H. Ji
Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurlPS), 2024
Pseudo-Siamese directional transformers for Self-supervised real-world denoising
Y. Quan, T. Zheng, and H. Ji
Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurlPS), 2024
Phase unwrapping via fully exploiting global and local spatial dependencies [manuscript][supp]
Y. Quan, X. Yao, Z. Chen✉, and H. Ji
Optics and Laser Technology, 2024
Deep single image defocus deblurring via gaussian kernel mixture learning [manuscript]
Y. Quan, Z. Wu, R. Xu✉, and H. Ji
IEEE Transactions on Patter Analysis and Machine Intelligence (TPAMI), 2024
Dual-path deep unsupervised learning for multi-focus image fusion [manuscript][supp]
Y. Quan, X. Wan, T. Zheng, Y. Huang✉, and H. Ji
IEEE Transactions on Multimedia (TMM), 2024
Enhancing underwater images via asymmetric multi-scale invertible networks [manuscript][supp]
Y. Qaun, X. Tan, Y. Huang✉, Y. Xu, and H. Ji
ACM Multimedia (MM), 2024
Highly efficient no-reference 4K video quality assessment with full-pixel covering sampling and training strategy [manuscript]
X. Tan, J. Zhang, Y. Quan✉, J. Li✉, Y, Wu, and Z. Bian
ACM Multimedia (MM), 2024
3D Snapshot: Invertible embedding of 3D neural representations in a single image
Y. Lu, B. Deng, Z. Zhong, T. Zhang, Y. Quan, H. Cai, and S. He
IEEE Transactions on Patter Analysis and Machine Intelligence (TPAMI), 2024

2024

Text-guided portrait image matting [manuscript]
Y. Xu, X. Yao, B. Liu, Y. Quan✉, and H. Ji
IEEE Transactions on Artificial Intelligence (TAI), 5(8): 4149-4162, 2024
Unsupervised deep unrolling networks for phase unwrapping [manuscript][supp][github]
Z. Chen, Y. Quan✉, and H. Ji
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Siamese cooperative learning for unsupervised image reconstruction from incomplete measurements [manuscript][github]
Y. Quan, X. Qin✉, T. Pang, and H. Ji
IEEE Transactions on Patter Analysis and Machine Intelligence (TPAMI), 46(7): 4866-4879, 2024
Enhanced Deep Unrolling Networks for Snapshot Compressive Hyperspectral Imaging [manuscript]
X. Qin, Y. Quan✉, and H. Ji
Neural Networks (NN), 174, 2024
Enhancing texture representation with deep tracing pattern encoding [manuscript]
Z. Chen, Y. Quan, R. Xu✉, L. Jin, and Y. Xu
Pattern Recognition (PR), 146, 2024
Wavelet analysis model inspired convolutional neural networks for image denoising [manuscript]
R. Xu, Y. Xu, X. Yang, H. Huang, Z. Lei, and Y. Quan✉
Applied Mathematical Modelling (AMM), 125: 798-811, 2024
Image smoothing via multiscale global perception [manuscript][supp][github]
X. He, Y. Quan, R. Xu✉, and Y. Xu
IEEE Signal Processing Letters (SPL), 31: 411-415, 2024

2023

Single image defocus deblurring via implicit neural inverse kernels [manuscript][supp][github]
Y. Quan, X. Yao, and H. Ji
International Conference on Computer Vision (ICCV), 2023
Fingerprinting deep image restoration models [manuscript][supp][github]
Y. Quan, H. Teng, R. Xu✉, J. Huang, and H. Ji
International Conference on Computer Vision (ICCV), 2023
Deep video demoiréing via compact invertible dyadic decomposition [manuscript][supp][github]
Y. Quan, H. Huang, S. He, and R. Xu✉
International Conference on Computer Vision (ICCV), 2023
Diffuse3D: Wide-angle 3D photography via bilateral diffusion [manuscript]
Y. Jiang, Y. Zhou, Y. Liang, W. Liu, J. Jiao, Y. Quan, and S. He✉
International Conference on Computer Vision (ICCV), 2023
Video noise removal using progressive decomposition with conditional invertibility [manuscript]
H. Huang, Y. Quan, Z. Lei, J. Hu, and Y. Huang✉
IEEE International Conference on Multimedia and Expo (ICME), 2023
Image desnowing via deep invertible separation [manuscript][github]
Y. Quan, X. Tan, Y. Huang✉, Y. Xu, and H. Ji
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 33(7): 3133-3144, 2023
Ground-truth free meta-learning for deep compressive sampling [manuscript][supp]
X. Qin, Y. Quan✉, T. Pang, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Neumann network with recursive kernels for single image defocus deblurring [manuscript][supp]
Y. Quan, Z. Wu, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Unsupervised deep learning for phase retrieval via teacher-student distillation [manuscript][github]
Y. Quan, Z. Chen✉, T. Pang, and H. Ji
AAAI Conference on Artificial Intelligence (AAAI), Oral, 2023
Self-supervised blind image deconvolution via deep generative ensemble learning [manuscript]
M. Chen, Y. Quan✉, Y. Xu, and H. Ji
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 33(2): 634-647, 2023

2022

Dual-domain self-supervised learning and model adaption for deep compressive imaging [manuscript][github]
Y. Quan, X. Qin✉, T. Pang, and H. Ji
European Conference on Computer Vision (ECCV), 2022
Learning deep non-blind image deconvolution without ground truths [manuscript]
Y. Quan, Z. Chen✉, H. Zheng, and H. Ji
European Conference on Computer Vision (ECCV), 2022
Self-supervised low-light image enhancement using discrepant untrained network priors [manuscript][supp][github]
J. Liang, Y. Xu, Y. Quan✉, B. Shi, and H. Ji
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 32(11): 7332-7345, 2022
Nonblind image deblurring via deep learning in complex field [manuscript][supp]
Y. Quan, P. Lin, Y. Xu✉, Y. Nan, and H. Ji
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 33(10): 5387-5400, 2022
Unsupervised knowledge transfer for nonblind image deconvolution [manuscript]
Z. Chen, X. Yao, Y. Xu, J. Wang, and Y. Quan✉
Pattern Recognition Letters, 164: 232–238, 2022
A dataset-free deep learning method for low-dose CT image reconstruction [manuscript]
Q. Ding, H. Ji, Y. Quan, and X. Zhang
Inverse Problems (IP), 38, 104003, 2022
No-reference image quality assessment using dynamic complex-valued neural model [manuscript]
Z. Zhou, Y. Xu, R. Xu✉, and Y. Quan
ACM Multimedia (MM), 2022
Deep blind image quality assessment using dual-order statistics [manuscript]
Z. Zhou, Y. Xu, Y. Quan, and R. Xu✉
IEEE International Conference on Multimedia and Expo (ICME), 2022
Nonblind image deconvolution via leveraging model uncertainty in an untrained deep neural network [manuscript][supp][github]
M. Chen, Y. Quan✉, T. Pang, and H. Ji
International Journal of Computer Vision (IJCV), 130: 1770–1789, 2022
Unsupervised phase retrieval using deep approximate MMSE estimation [manuscript][supp][github]
M. Chen, P. Lin, Y. Quan✉, T. Pang, and H. Ji
IEEE Transactions on Signal Processing (TSP), 70: 2239–2252, 2022
Unsupervised deep background matting using deep matte prior [manuscript][supp][github]
Y. Xu, B. Liu, Y. Quan✉, and H. Ji
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 32(7): 4324–4337, 2022
High-quality self-supervised snapshot hyperspectral imaging [manuscript][github]
Y. Quan, X. Qin, M. Chen, and Y. Huang✉
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022
Recurrent exposure generation for low-light face detection [manuscript][github]
J. Liang, J. Wang, Y. Quan, T. Chen, J. Liu, H. Ling, and Y. Xu✉
IEEE Transactions on Multimedia (TMM), 24: 1609–1621, 2022

2021

Gaussian kernel mixture network for single image defocus deblurring [manuscript][supp][github]
Y. Quan, Z. Wu, and H. Ji
Advances in Neural Information Processing Systems (NeurIPS), 2021
Encoding spatial distribution of convolutional features for texture representation [manuscript][supp][github]
Y. Xu, F. Li, Z. Chen, J. Liang, and Y. Quan✉
Advances in Neural Information Processing Systems (NeurIPS), 2021
Deep texture recognition via exploiting cross-layer statistical self-similarity [manuscript]
Z. Chen, F. Li, Y. Quan✉, Y. Xu, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Recorrupted-to-Recorrupted: Unsupervised deep learning for image denoising [manuscript][supp][github]
T. Pang, H. Zheng, Y. Quan, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Multi-view 3D shape recognition via correspondence-aware deep learning [manuscript]
Y. Xu, C. Zheng, R. Xu, Y. Quan✉, and H. Ling
IEEE Transactions on Image Processing (TIP), 30: 5299–5312, 2021
Image quality assessment using kernel sparse coding [manuscript][supp][code][github]
Z. Zhou, J. Li, Y. Quan✉, and R. Xu
IEEE Transactions on Multimedia (TMM), 23: 1592–1604, 2021
Watermarking deep neural networks in image processing [manuscript][github]
Y. Quan, H. Teng, Y. Chen, and H. Ji✉
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 32(5): 1852–1865, 2021
Factorized tensor dictionary learning for visual tensor data completion [manuscript][code]
R. Xu, Y. Xu, and Y. Quan✉
IEEE Transactions on Multimedia (TMM), 23: 1225–1238, 2021
Attentive deep network for blind motion deblurring on dynamic scenes [manuscript][github]
Y. Xu, Y. Zhu, Y. Quan✉, and H. Ji
Computer Vision and Image Understanding (CVIU), 205, 2021
Image denoising using complex-valued deep CNN [manuscript][github]
Y. Quan, Y. Chen, Y. Shao, H. Teng, Y. Xu✉, and H. Ji
Pattern Recognition (PR), 111, 2021
Structure-texture image decomposition using discriminative patch recurrence [manuscript][supp][code][github]
R. Xu, Y. Xu, and Y. Quan✉
IEEE Transactions on Image Processing (TIP), 30: 1542-1555, 2021

2020

Self-supervised Bayesian deep learning for image recovery with applications to compressed sensing [manuscript][supp][github]
T. Pang, Y. Quan, and H. Ji
European Conference on Computer Vision (ECCV), 2020
Full-reference image quality metric for blurry images and compressed images using hybrid dictionary learning [manuscript][github]
Z. Zhou, J. Li, Y. Xu, and Y. Quan✉
Neural Computing and Applications (NCA), 32(16): 12403-12415, 2020
Cartoon-texture image decomposition using orientation characteristics in patch recurrence [manuscript]
R. Xu, Y. Xu, Y. Quan✉, and H. Ji
SIAM Journal on Imaging Sciences (SIIMS), 13(3): 1179–1210, 2020
Self2Self with dropout: Learning self-supervised denoising from single image [manuscript][supp][code][github]
Y. Quan, M. Chen, T. Pang, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Variational-EM-based deep learning for noise-blind image deblurring [manuscript]
Y. Nan, Y. Quan, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Collaborative deep learning for super-resolving blurry text images [manuscript][github]
Y. Quan, J. Yang, Y. Chen, Y. Xu✉, and H. Ji
IEEE Transactions on Computational Imaging (TCI), 6: 778-790, 2020
Image denoising via sequential ensemble learning [manuscript][github]
X. Yang, Y. Xu, Y. Quan✉, and H. Ji
IEEE Transactions on Image Processing (TIP), 29: 5038-5049, 2020
Weakly-supervised sparse coding with geometric prior for interactive texture segmentation [manuscript][supp][github]
Y. Quan, H. Teng, T. Liu, and Y. Huang✉
IEEE Signal Processing Letters (SPL), 27: 116-120, 2020
Removing reflection from a single image with ghosting effect [manuscript]
Y. Huang, Y. Quan✉, Y. Xu, R. Xu, and H. Ji
IEEE Transactions on Computational Imaging (TCI), 6: 34-45, 2020

2019

Barzilai-Borwein-based adaptive learning rate for deep learning [manuscript][github]
J. Liang, Y. Xu, C. Bao, Y. Quan✉, and H. Ji
Pattern Recognition Letters (PRL), 128: 197-203, 2019
Exploiting global low-rank structure and local sparsity nature for tensor completion [manuscript][github]
Y. Du, G. Han✉, Y. Quan, Z. Yu, H. Wong, C. Chen, and J. Zhang
IEEE Transactions on Cybernetics (TCYB), 49(11): 3898-3910, 2019
Deep learning for seeing through window with raindrops [manuscript][supp][github]
Y. Quan, S. Deng, Y. Chen, and H. Ji
IEEE International Conference on Computer Vision (ICCV), 2019
Attention with structure regularization for action recognition [manuscript]
Y. Quan, Y. Chen, R. Xu✉, and H. Ji
Computer Vision and Image Understanding (CVIU), 187, 2019
Supervised sparse coding with decision forest [manuscript][github]
Y. Huang, Y. Quan✉, and T. Liu
IEEE Signal Processing Letters (SPL), 26(2): 327-331, 2019

2017 - 2018

Image-based action recognition using hint-enhanced deep neural network [manuscript]
T. Qi, Y. Xu✉, Y. Quan, Y. Wang, and H. Ling
Neurocomputing (NC), 267: 475-488, 2017
Spatiotemporal lacunarity spectrum for dynamic texture classification [manuscript]
Y. Quan, Y. Sun✉, and Y. Xu
Computer Vision and Image Understanding (CVIU), 165: 85-96, 2017
Estimating defocus blur via rank of local patches [manuscript][supp][code]
G. Xu, Y. Quan, and H. Ji
IEEE International Conference on Computer Vision (ICCV), 2017

2015 - 2016

Dictionary learning for sparse coding: Algorithms and convergence analysis [manuscript][code]
C. Bao, H. Ji✉, Y. Quan, and Z. Shen
IEEE Transactions on Patter Analysis and Machine Intelligence (TPAMI), 38(7): 1356-1369, 2016
Supervised dictionary learning with multiple classifier integration [manuscript][code]
Y. Quan, Y. Xu✉, Y. Sun, and Y. Huang
Pattern Recognition (PR), 55: 247-260, 2016
Equiangular kernel dictionary learning with applications to dynamic texture analysis [manuscript][supp]
Y. Quan, C. Bao, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Sparse coding for classification via discrimination ensemble [manuscript]
Y. Quan, Y. Xu, Y. Sun, Y. Huang, and H. Ji
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Dynamic texture recognition via orthogonal tensor dictionary learning [manuscript]
Y. Quan, Y. Huang, and H. Ji
IEEE International Conference on Computer Vision (ICCV), 2015
Classifying dynamic textures via spatiotemporal fractal analysis [manuscript]
Y. Xu, Y. Quan✉, Z. Zhang, H. Ling, and H. Ji
Pattern Recognition (PR), 48(10): 3239-3248, 2015
Structured sparse coding for classification via reweighted l_2,1 minimization [manuscript]
Y. Xu, Y. Sun, Y. Quan, and Y. Luo
The Chinese Conference on Computer Vision (CCCV), 2015
Fractal analysis for reduced reference image quality assessment [manuscript]
Y. Xu✉, D. Liu, Y. Quan, and P. Callet
IEEE Transactions on Image Processing (TIP), 24(7): 2089-2109, 2015
Discriminative structured dictionary learning with hierarchical group sparsity [manuscript][code]
Y. Xu✉, Y. Sun, Y. Quan, and B. Zheng
Computer Vision and Image Understanding (CVIU), 136: 59-68, 2015
Characterizing dynamic textures with space-time lacunarity analysis [manuscript]
Y. Sun, Y. Xu, and Y. Quan
IEEE International Conference on Multimedia and Expo (ICME), Oral, 2015
Directional regularity for visual quality estimation [manuscript]
D. Liu, Y. Xu✉, Y. Quan, Z. Yu, and P. Callet
Signal Processing (SP), 110: 211-221, 2015
Data-driven multi-scale non-local wavelet frame construction and image recovery [manuscript][code]
Y. Quan, H. Ji✉, and Z. Shen
Journal of Scientific Computing (JoSC), 63(2): 307-329, 2015

2013 - 2014

A convergent incoherent dictionary learning algorithm for sparse coding [manuscript]
C. Bao, Y. Quan, and H. Ji
European Conference on Computer Vision (ECCV), 2014
Reduced reference image quality assessment using regularity of phase congruency [manuscript][code]
D. Liu, Y. Xu✉, Y. Quan, and P. Callet
Signal Processing: Image Communication (SPIC), 29(8): 844-855, 2014
L₀ norm based dictionary learning by proximal methods with global convergence [manuscript][code]
C. Bao, H. Ji, Y. Quan, and Z. Shen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2014
Lacunarity analysis on image patterns for texture classification [manuscript]
Y. Quan, Y. Xu, Y. Sun, and Y. Luo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
A distinct and compact texture descriptor [manuscript][code]
Y. Quan, Y. Xu, and Y. Sun
Image and Vision Computing (IVC), 32(4): 250-259, 2014

2011 - 2012

Contour-based recognition [manuscript][code]
Y. Xu, Y. Quan, Z. Zhang, H. Ji, C. Fermüller M. Nishigaki, and D. Dementhon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
Dynamic texture classification using dynamic fractal analysis [manuscript][code]
Y. Xu, Y. Quan, H. Ling, and H. Ji
IEEE International Conference on Computer Vision (ICCV), 2011