Jiale Lin

Westlake University
AI Physics Lab

Hangzhou, China

github.com/jialelin2007

scholar.google.com/citations?user=UuJy0LAAAAAJ

huggingface.co/jialelin2007

I am a second-year undergraduate student at Westlake University, working with the AI Physics Lab. My current work sits at Computational Imaging, AI for Science, and Image Generation.

My recent projects focus on Thermal-Infrared Hyperspectral Imaging, Heat Assisted Detection and Ranging, and physically grounded image restoration. I am especially interested in methods that connect image formation physics with practical learning systems.

Research Interests

Computational Thermal Imaging and Long-Wave Infrared Hyperspectral Imaging
HADAR, TeX Decomposition, and physically constrained inverse problems

Recent Work

TeX-1500: A paired real-world LWIR hyperspectral dataset and benchmark for supervised HSI-to-TeX decomposition.
HAIR: HADAR-based image restoration for Thermal-Infrared Hyperspectral imagery, combining sensor-aware restoration with thermal physics and atmospheric downwelling references.
TAG: Thermal anti-ghosting work for material-nonuniform computational night vision and high-fidelity thermal perception.

News

Jun 03, 2026	Launched this academic homepage as a public entry point for Research Projects, Code, Datasets, and Publication Records.
Jun 02, 2026	TeX-1500 was released as a paired real-world LWIR Hyperspectral Dataset and benchmark for Temperature-Emissivity-Texture Decomposition.
May 13, 2026	HAIR was released as a physics-driven framework for HADAR-Based Thermal Infrared Hyperspectral Image Restoration.
Apr 02, 2026	TAG was released as a Universal Computational Thermal Imaging framework for addressing the ghosting effect in thermal perception.

Selected Publications

arXiv

TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature–Emissivity–Texture Decomposition

Cheng Dai^*, Jiale Lin^*, Hongyi Xu, Bingxuan Song, Ziyang Xie, and Fanglin Bao

^*Equal Contribution, preprint , 2026

arXiv Bib Code Data and Checkpoint

@misc{dai2026tex1500,
  title = {TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature--Emissivity--Texture Decomposition},
  author = {Dai, Cheng and Lin, Jiale and Xu, Hongyi and Song, Bingxuan and Xie, Ziyang and Bao, Fanglin},
  year = {2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}

arXiv

HADAR-Based Thermal Infrared Hyperspectral Image Restoration

Cheng Dai^*, Jiale Lin^*, Bingxuan Song, Yifei Chen, Jiashuo Chen, Xin Yuan, and 1 more author

^*Equal Contribution, preprint , 2026

arXiv Bib Code

@misc{dai2026hadarbased,
  title = {HADAR-Based Thermal Infrared Hyperspectral Image Restoration},
  author = {Dai, Cheng and Lin, Jiale and Song, Bingxuan and Chen, Yifei and Chen, Jiashuo and Yuan, Xin and Bao, Fanglin},
  year = {2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}

arXiv

Universal Computational Thermal Imaging Overcoming the Ghosting Effect

Hongyi Xu, Du Wang, Chenjun Zhao, Jiashuo Chen, Jiale Lin, Liqin Cao, and 3 more authors

preprint , 2026

arXiv Bib

@misc{xu2026universal,
  title = {Universal Computational Thermal Imaging Overcoming the Ghosting Effect},
  author = {Xu, Hongyi and Wang, Du and Zhao, Chenjun and Chen, Jiashuo and Lin, Jiale and Cao, Liqin and Zhong, Yanfei and She, Yiyuan and Bao, Fanglin},
  year = {2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}