Zi Wang

I am a fifth-year PhD student in a cooperative education program between Shanghaitech University and Shanghai Institute of Technical Physics, Chinese Academy of Sciences. I am advised by Jingyi Yu, Jianyu Wang, and Chunlai Li.

I received B.S. of Electronic Engineering from Beihang University in 2019. I am planning to complete my PhD. degree in summer, 2025. And I am now looking for a postdoc position in 2025 fall.

My research interest is focused on the integration of deep learning, computational imaging, and spectrum reconstruction. I believe that modern deep learning techniques will revolutionize our perception of the world.

School Email: wangzi@shanghaitech.edu.cn

Personal Email: zeromakerwz@foxmail.com

CV / Google Scholar

Representative papers

	Robust gas species and concentration monitoring via cross-talk transformer with snapshot infrared spectral imager Yang Yang^†, Zi Wang^†, Pengyu Wang, Guoliang Tang, Chengyu Liu, Chunlai Li, Jianyu Wang †: Equal contributions. : Corresponding author. Sensors and Actuators B: Chemical(SNB)* , 2024 We propose the cross-talk transformer for fast and accurate gas identification and concentration estimation via hyperspectral infrared spectrometer.
	Single-pixel p-graded-n junction spectrometers Jingyi Wang^†, Beibei Pan^†, Zi Wang^†, Jiakai Zhang, Zhiqi Zhou, Lu Yao, Yanan Wu, Wuwei Ren, Jianyu Wang, Haiming Ji, Jingyi Yu, Baile Chen †: Equal contributions. : Corresponding author. Nature Communications(NC)* , 2024 arXiv / data / Supplementary Information We propose a III-V material based um-size miniaturized spectrometers with tailored Neural Spectral Fields (NSF) method to achieve 0.30nm wavelength accuracy and 10 nm spectral resolution.
	Non-line-of-sight imaging via neural transient fields Siyuan Shen^†, Zi Wang^†, Ping Liu, Zhengqing Pan, Ruiqian Li, Tian Gao, Shiying Li, Jingyi Yu †: Equal contributions. : Corresponding author. IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI)* , July 2021 project page / arXiv / code We propose the neural transient fields with Non-line-of-sight(NLOS) rendering methods to solve the NLOS imaging problem.

Other papers

	Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention Mechanisms Yanhua Yu, Siyuan Shen, Zi Wang, Binbin Huang, Yuehan Wang, Xingyue Peng, Suan Xia, Ping Liu, Ruiqian Li, Shiying Li* : Corresponding author. IEEE/CVF International Conference on Computer Vision (ICCV)*, 2023 Webpage / CVF webpage / IEEE webpage / Code We propose a novel approach that enhances physics-based NLOS imaging methods by introducing a learnable inverse kernel in the Fourier domain and using an attention mechanism to improve the neural network to learn high-frequency information.
	Short-Wave Infrared Chip-Spectrometer by Using Laser Direct-Writing Grayscale Lithography Zhiyi Xuan, Zi Wang, Qingquan Liu, Songlei Huang, Bo Yang, Liyi Yang, Zhiqin Yin, Maobin Xie, Chenlu Li, Jingyi Yu, Shaowei Wang, Wei Lu, : Corresponding author. Advanced Optical Materials(AOM), October, 2022 We propose a Short-wave Infrared (SWIR) computational spectrometer achieving 2 nm spectral resolution in a wide range from 900 to 1700 nm.
	Onsite Non-Line-of-Sight Imaging via Online Calibration Zhengqing Pan, Ruiqian Li, Tian Gao, Zi Wang, Siyuan Shen, Ping Liu, Tao Wu, Jingyi Yu, Shiying Li : Corresponding author. IEEE Photonics Journal*, October 2022 project page / arXiv / IEEE webpage / code We propose a physics-based calibration method for transient imaging including Line-of-sight(LOS) and Non-line-of-sight(NLOS) imaging.
	Real-Time Hyperspectral Video Acquisition with Coded Slits Guoliang Tang, Zi Wang, Shijie Liu, Chunlai Li, Jianyu Wang : Corresponding author. Sensors*, 2022 We propose the coded slits to achieve real-time hyperspectral video acquisition. The video rate reaches 5Hz.

The page source code is from Jon Barron.