Zi Wang

Dr. Zi Wang

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 April 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SSSiyuan Shen
Siyuan Shen
ZWZi Wang
Zi Wang
PLPing Liu
Ping Liu
ZPZhengqing Pan
Zhengqing Pan
RLRuiqian Li
Ruiqian Li
JYJingyi Yu
Jingyi Yu
We present a neural modeling framework for non-line-of-sight (NLOS) imaging. Previous solutions have sought to explicitly recover the 3D geometry (e.g., as point clouds) or voxel density (e.g., within a pre-defined volume) of the hidden scene. In contrast, inspired by the recent Neural Radiance Field (NeRF) approach, we use a multi-layer perceptron (MLP) to represent the neural transient field or NeTF. However, NeTF measures the transient over spherical wavefronts rather than the radiance along lines. We therefore formulate a spherical volume NeTF reconstruction pipeline, applicable to both confocal and non-confocal setups. Compared with NeRF, NeTF samples a much sparser set of viewpoints (scanning spots) and the sampling is highly uneven. We thus introduce a Monte Carlo technique to improve the robustness in the reconstruction. Experiments on synthetic and real datasets demonstrate NeTF achieves state-of-the-art performance and can provide reliable reconstructions even under semi-occlusions and on non-Lambertian materials.

27 February 2024 in Nature Communications
Verified
Journal Article
Open access
PDF file
JWJingyi Wang
Jingyi Wang
BPBeibei Pan
Beibei Pan
ZWZi Wang
Zi Wang
JZJiakai Zhang
Jiakai Zhang
ZZZhiqi Zhou
Zhiqi Zhou
BCBaile Chen
Baile Chen
Ultra-compact spectrometers are becoming increasingly popular for their promising applications in biomedical analysis, environmental monitoring, and food safety. In this work, we report a single-pixel-photodetector spectrometer with a spectral range from 480 nm to 820 nm, based on the AlGaAs/GaAs p-graded-n junction with a voltage-tunable optical response. To reconstruct the optical spectrum, we propose a tailored method called Neural Spectral Fields (NSF) that leverages the unique wavelength and bias-dependent responsivity matrix. Our spectrometer achieves a high spectral wavelength accuracy of up to 0.30 nm and a spectral resolution of up to 10 nm. Additionally, we demonstrate the high spectral imaging performance of the device. The compatibility of our demonstration with the standard III-V process greatly accelerates the commercialization of miniaturized spectrometers.

10 April 2024 in Sensors and Actuators B: Chemical
Verified
Journal Article
Closed access
YYYang Yang
Yang Yang
ZWZi Wang
Zi Wang
PWPengyu Wang
Pengyu Wang
GTGuoliang Tang
Guoliang Tang
CLChengyu Liu
Chengyu Liu
JWJian-yu Wang
Jian-yu Wang

21 January 2022 in Sensors
Verified
Journal Article
Open access
PDF file
GTGuoliang Tang
Guoliang Tang
ZWZi Wang
Zi Wang
LSLiu Shijie
Liu Shijie
LCLi Chunlai
Li Chunlai
JWJian-yu Wang
Jian-yu Wang
We propose a real-time hyperspectral video acquisition system that uses coded slits. Conventional imaging spectrometers usually have scanning mechanisms that reduce the temporal resolution or sacrifice the spatial resolution to acquire spectral information instantly. Recently, computational spectral imaging has been applied to realize high-speed or high-performance spectral imaging. However, the most current computational spectral imaging systems take a long time to reconstruct spectral data cubes from limited measurements, which limits real-time hyperspectral video acquisition. In this work, we propose a new computational spectral imaging system. We substitute the slit in a conventional scanning-based imaging spectrometer with coded slits, which can achieve the parallel acquisition of spectral data and thus an imaging speed that is several times higher. We also apply an electronically controlled translation stage to use different codes at each exposure level. The larger amount of data allows for fast reconstruction through matrix inversion. To solve the problem of a trade-off between imaging speed and image quality in high-speed spectral imaging, we analyze the noise in the system. The severe readout noise in our system is suppressed with S-matrix coding. Finally, we build a practical prototype that can acquire hyperspectral video with a high spatial resolution and a high signal-to-noise ratio at 5 Hz in real time.

29 November 2024 in Sensors
Verified
Journal Article
Open access
PDF file
ZWZi Wang
Zi Wang
YYYang Yang
Yang Yang
LYLiyin Yuan
Liyin Yuan
LCLi Chunlai
Li Chunlai
JWJian-yu Wang
Jian-yu Wang
Long-wave infrared (LWIR) spectral imaging plays a critical role in various applications such as gas monitoring, mineral exploration, and fire detection. Recent advancements in computational spectral imaging, powered by advanced algorithms, have enabled the acquisition of high-quality spectral images in real time, such as with the Uncooled Snapshot Infrared Spectrometer (USIRS). However, the USIRS system faces challenges, particularly a low spectral resolution and large amount of data noise, which can degrade the image quality. Deep learning has emerged as a promising solution to these challenges, as it is particularly effective at handling noisy data and has demonstrated significant success in hyperspectral imaging tasks. Nevertheless, the application of deep learning in LWIR imaging is hindered by the severe scarcity of long-wave hyperspectral image data, which limits the training of robust models. Moreover, existing networks that rely on convolutional layers or attention mechanisms struggle to effectively capture both local and global spectral correlations. To address these limitations, we propose the pixel-based Hierarchical Spectral Transformer (HST), a novel deep learning architecture that learns from publicly available single-pixel long-wave infrared spectral databases. The HST is designed to achieve a high spectral resolution for LWIR spectral image reconstruction, enhancing both the local and global contextual understanding of the spectral data. We evaluated the performance of the proposed method on both simulated and real-world LWIR data, demonstrating the robustness and effectiveness of the HST in improving the spectral resolution and mitigating noise, even with limited data.

14 September 2021 in arXiv
Verified
Preprint
Open access
PDF file
SSSiyuan Shen
Siyuan Shen
ZWZi Wang
Zi Wang
PLPing Liu
Ping Liu
ZPZhengqing Pan
Zhengqing Pan
RLRuiqian Li
Ruiqian Li
JYJingyi Yu
Jingyi Yu
We present a neural modeling framework for Non-Line-of-Sight (NLOS) imaging. Previous solutions have sought to explicitly recover the 3D geometry (e.g., as point clouds) or voxel density (e.g., within a pre-defined volume) of the hidden scene. In contrast, inspired by the recent Neural Radiance Field (NeRF) approach, we use a multi-layer perceptron (MLP) to represent the neural transient field or NeTF. However, NeTF measures the transient over spherical wavefronts rather than the radiance along lines. We therefore formulate a spherical volume NeTF reconstruction pipeline, applicable to both confocal and non-confocal setups. Compared with NeRF, NeTF samples a much sparser set of viewpoints (scanning spots) and the sampling is highly uneven. We thus introduce a Monte Carlo technique to improve the robustness in the reconstruction. Comprehensive experiments on synthetic and real datasets demonstrate NeTF provides higher quality reconstruction and preserves fine details largely missing in the state-of-the-art.