Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
HADAR: Toward a New Visual Modality Beyond Appearance
Published:
Most machine vision systems still see the world through proxies. RGB records how a scene appears under visible illumination. Depth sensors estimate geometry by projecting or receiving structured signals. These modalities have enabled remarkable progress, but they do not directly describe the stable physical properties of objects. They are sensitive to lighting, weather, surface reflectance, transparency, and occlusion.
publications
HADAR-Based Thermal Infrared Hyperspectral Image Restoration
Published in arXiv, 2026
We propose HAIR, a physics-driven framework for ground-based thermal-infrared hyperspectral image restoration. HAIR combines the HADAR rendering equation with atmospheric downwelling radiative transfer to restore TIR-HSI through physically interpretable temperature, emissivity, and texture components.
Recommended citation: Cheng Dai, Jiale Lin, Bingxuan Song, Yifei Chen, Jiashuo Chen, Xin Yuan, and Fanglin Bao. (2026). "HADAR-Based Thermal Infrared Hyperspectral Image Restoration." arXiv preprint arXiv:2605.13664.
Download Paper
TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature-Emissivity-Texture Decomposition
Published in arXiv, 2026
We introduce TeX-1500, a paired real-world long-wave infrared hyperspectral dataset and benchmark for supervised temperature-emissivity-texture decomposition, together with TeX-UNet as a wavelength-aware baseline.
Recommended citation: Cheng Dai, Jiale Lin, Hongyi Xu, Bingxuan Song, Ziyang Xie, and Fanglin Bao. (2026). "TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature-Emissivity-Texture Decomposition." arXiv preprint arXiv:2606.03806.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
B.Eng. in Communication Engineering
Education, 2021-2025, School of Communication Engineering, Jilin University, 2021
Undergraduate study in communication engineering at Jilin University.
AI Engineering Intern
Internship, 2024.12-2025.02, Lightwheel AI, 2024
Internship focused on embodied AI asset construction, RoboCasa plugin development, and teleoperation tooling.
Audio AI Intern
Internship, 2025.04-2025.09, Amoon AI, 2025
Internship on low-resource infant-cry activity detection and state classification, covering dataset curation, audio foundation-model fine-tuning, Conformer training, VAD design, and edge deployment.
Graduate Study in Communication Engineering
Education, 2025-2026, State Key Laboratory of Surveying, Mapping and Remote Sensing Information Engineering, Wuhan University, 2025
Graduate study in communication engineering at Wuhan University, followed by a voluntary withdrawal due to a research-field mismatch.
Research Assistant, AI for Physics Lab
Research Experience, 2025-2026, AI for Physics Lab, Westlake University, 2025
Research assistant in the AI for Physics Lab, advised by Xin Yuan and Fanglin Bao, leading AI-side efforts for HADAR algorithms and lightweight deployment.