Biography

I am now an Associate Professor at Westlake University in  Hangzhou, Zhejiang, China.  I am working on computational imaging and machine learning。

I was a video analysis and coding lead researcher at Bell Labs, Nokia, 600 Mountain Ave, Murray Hill, NJ 07974 from 2015 to 021. Before this, I was a Postdoctoral Associate in Department of Electrical and Computer Engineering, Duke University, Durham, NC, 27708.

News: 

3/27 /2023:  One  paper accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). 

3/20 /2023:  One  paper accepted by APL Photonics. 

3/16 /2023:  One  paper accepted by Journal of Physics D: Applied Physics.

3/6/2023:  One paper accepted by International Journal of Computer Vision (IJCV).

2/28 /2023:  One paper accepted by CVPR 2023.

1/21 /2023:  One paper accepted by ICLR 2023.

My research interests are computational imaging, machine learning, computer vision, signal processing and image processing. You can check my recent papers at https://scholar.google.com/citations?hl=en&user=cS9CbWkAAAAJ&view_op=list_works&sortby=pubdate  and reach me at eiexyuan@gmail.com or xinyuan.sci@outlook.com .

Since 2012, Dr. Yuan's main research topic is computational imaging, which includes the hardware system design (usually using optics, please refer to papers published in CVPR, ECCV, Optica, Optics Letters, Optics Express and APL Photonics), and algorithm development including optimization based algorithms (please refer to papers listed below published in IEEE T-PAMI, T-IP and T-SP) and deep-learning-based algorithms (please refer to papers published in CVPR, ICCV and ECCV). Furthermore, Dr. Yuan works with colleagues on the theoretical derivation of computational imaging systems (please refer to papers listed below published in IEEE T-IT). Dr. Yuan also works on machine learning models for other data analysis (please refer to papers published in ICML, NIPS and AISTATS).

Currently, Dr. Yuan is working on the Snapshot Compressive Imaging (refer to the review paper published in IEEE Signal Processing Magazine entitled "Snapshot Compressive Imaging: Theory, Algorithms and Applications" doi: 10.1109/MSP.2020.3023869), dubbed SCI.  Snapshot compressive imaging uses a two-dimensional (2D) detector to capture high-dimensional (HD, i.e., 3D or larger) data in a snapshot measurement. Via novel optical designs, the 2D detector samples the HD data in a compressive manner; following this, algorithms are employed to reconstruct the desired HD data-cube. SCI has been used in hyperspectral imaging, video, holography, tomography, focal depth imaging, polarization imaging, microscopy, etc. Though the hardware has been investigated for more than a decade, the theoretical guarantees have only recently been derived in 2019. Inspired by deep learning, various deep neural networks have also been developed to reconstruct the HD data-cube in spectral SCI and video SCI. Dr. Yuan and his collaborators are leading the state-of-the-art SCI reconstruction algorithms, both in optimization (T-PAMI 2019) and deep learning (CVPR 2020, CVPR 2021 and ECCV 2020).

In addition to SCI, Dr. Yuan is also working on other image processing algorithms, such as denoising, inpainting, deblocking, and other image restoration tasks (please refer to papers listed below published in IEEE T-IP).

Before 2012, Dr. Yuan was working on array signal processing, especially on the polarization antenna array signal processing (please refer to papers published in IEEE T-SP, T-AES and T-AP).

Dr. Yuan is the author/co-author of 2 book chapters, >70 journal papers and >60 conference papers. Some prestigious journals include: IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Signal Processing Magazine,  IEEE Transactions on Image Processing, IEEE Transactions on Signal Processing, Optica, Optics Letters and top-tier conferences such as IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision (ICCV), European Conference on Computer Vision (ECCV), International Conference on Machine Learning (ICML) and Conference on Neural Information Processing Systems (NeurIPS).

Dr. Yuan is the inventor/co-inventor of about 20 international patents.