# Yonsei STL

> Research project pages from Seamless Trans-X Lab, Yonsei University.

This file maps published project pages for agents that request it. It does not replace the HTML pages, the sitemap, or the papers.

## Publications

- [Publication index](https://yonsei-stl.github.io/publications/): Published Yonsei STL research project pages
- [RM-MLLM: Robust Scene Understanding in Adverse Weather with RGB-Multispectral Fusion](https://yonsei-stl.github.io/RM-MLLM/): A multispectral multimodal language model and the DENSE-QA benchmark for adverse-weather driving scene understanding, using synchronized RGB and multispectral images.
- [RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions](https://yonsei-stl.github.io/RASMD/): A large-scale driving dataset of 100,000 aligned RGB-SWIR pairs, with benchmarks for object detection and RGB-to-SWIR translation in adverse conditions.
- [RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution](https://yonsei-stl.github.io/RPT-SR/): A dual-token transformer for infrared super-resolution that combines learned regional priors with local features, evaluated on M3FD, RASMD, and TNO.
- [SpectraDiff: Enhancing the Fidelity of Infrared Image Translation with Object-Aware Diffusion](https://yonsei-stl.github.io/SpectraDiff/): A diffusion model that translates RGB images to infrared using semantic segmentation and a Spectral Attention Block, evaluated on FLIR, FMB, MFNet, IDD-AW, and RANUS.
- [Seeing through the rain: An empirical assessment of short-wave infrared imaging on enhancing autonomous vehicle perception under rainy weather](https://yonsei-stl.github.io/SeeingThroughRain/): A measurement-driven comparison of RGB and SWIR imaging in real rainy driving scenes using 620 paired frames, 14 image-quality metrics, visibility estimation, and fixed pretrained perception models.
- [Multi-Modal Cross-Attention-Based Multi-Label Weather and Severity Level Classification](https://yonsei-stl.github.io/MWSC/): MWSC jointly predicts multiple weather conditions and one severity level using global–local and image–text cross-attention, evaluated on 40,205 annotated driving images.
- [Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation](https://yonsei-stl.github.io/Pix2Next/): An RGB-to-NIR translation model that uses a vision foundation model, cross-attention, and a multi-scale PatchGAN, with results on RANUS, IDD-AW, and zero-shot BDD100K.
- [IVIFormer: Illumination-Aware Infrared-Visible Image Fusion via Adaptive Domain-Switching Cross Attention](https://yonsei-stl.github.io/IVIFormer/): IVIFormer adapts infrared–visible image fusion to day and night by switching the query and key/value domains in cross-attention, guided by a lightweight illumination classifier.
- [Short-Wave Infrared (SWIR) Imaging for Robust Material Classification: Overcoming Limitations of Visible Spectrum Data](https://yonsei-stl.github.io/SWIR-Material-Classification/): SWIR-based material discrimination of visually similar objects: real and artificial fruits and vegetables, humans, mannequins, and banners, using moisture-sensitive spectral bands.

## Bibliographic records

- [RM-MLLM: Robust Scene Understanding in Adverse Weather with RGB-Multispectral Fusion DOI](https://doi.org/10.1016/j.rineng.2026.112317)
- [RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions DOI](https://doi.org/10.1016/j.inffus.2025.103872)
- [RASMD arXiv](https://arxiv.org/abs/2504.07603)
- [RASMD dataset](https://huggingface.co/datasets/STL-Yonsei/RASMD/tree/main)
- [RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution DOI](https://doi.org/10.1109/WACV61042.2026.00503)
- [RPT-SR arXiv](https://arxiv.org/abs/2602.15490)
- [RPT-SR Code](https://github.com/Yonsei-STL/RPT-SR)
- [RPT-SR RASMD](https://yonsei-stl.github.io/RASMD/)
- [SpectraDiff: Enhancing the Fidelity of Infrared Image Translation with Object-Aware Diffusion DOI](https://doi.org/10.1016/j.cviu.2026.104709)
- [SpectraDiff code](https://github.com/Yonsei-STL/SpectraDiff)
- [Seeing through the rain: An empirical assessment of short-wave infrared imaging on enhancing autonomous vehicle perception under rainy weather DOI](https://doi.org/10.1016/j.measurement.2025.119654)
- [SeeingThroughRain Request data](mailto:shiho@yonsei.ac.kr?subject=Data%20request%3A%20Seeing%20through%20the%20rain)
- [Multi-Modal Cross-Attention-Based Multi-Label Weather and Severity Level Classification DOI](https://doi.org/10.1109/ACCESS.2025.3645363)
- [MWSC Code](https://github.com/Yonsei-STL/MWSC)
- [MWSC Annotations](https://github.com/Yonsei-STL/MWSC/tree/main/data/label)
- [Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation DOI](https://doi.org/10.3390/technologies13040154)
- [Pix2Next arXiv](https://arxiv.org/abs/2409.16706)
- [Pix2Next code](https://github.com/Yonsei-STL/pix2next/)
- [IVIFormer: Illumination-Aware Infrared-Visible Image Fusion via Adaptive Domain-Switching Cross Attention DOI](https://doi.org/10.1109/ICCVW69036.2025.00234)
- [IVIFormer Code](https://github.com/Yonsei-STL/IVIFormer)
- [Short-Wave Infrared (SWIR) Imaging for Robust Material Classification: Overcoming Limitations of Visible Spectrum Data DOI](https://doi.org/10.3390/app142311049)
- [SWIR-Material-Classification Dataset](https://huggingface.co/datasets/STL-Yonsei/SWIR-Fruit_and_Vegetable_Dataset)