RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915317162180608 |
|---|---|
| author | Jha, Raman Lenka, Adithya Ramanagopal, Mani Sankaranarayanan, Aswin Mitra, Kaushik |
| author_facet | Jha, Raman Lenka, Adithya Ramanagopal, Mani Sankaranarayanan, Aswin Mitra, Kaushik |
| contents | In nighttime conditions, high noise levels and bright illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementary information, offering richer textures and structural details. We propose RT-X Net, a cross-attention network that fuses RGB and thermal images for nighttime image enhancement. We leverage self-attention networks for feature extraction and a cross-attention mechanism for fusion to effectively integrate information from both modalities. To support research in this domain, we introduce the Visible-Thermal Image Enhancement Evaluation (V-TIEE) dataset, comprising 50 co-located visible and thermal images captured under diverse nighttime conditions. Extensive evaluations on the publicly available LLVIP dataset and our V-TIEE dataset demonstrate that RT-X Net outperforms state-of-the-art methods in low-light image enhancement. The code and the V-TIEE can be found here https://github.com/jhakrraman/rt-xnet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24705 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement Jha, Raman Lenka, Adithya Ramanagopal, Mani Sankaranarayanan, Aswin Mitra, Kaushik Computer Vision and Pattern Recognition In nighttime conditions, high noise levels and bright illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementary information, offering richer textures and structural details. We propose RT-X Net, a cross-attention network that fuses RGB and thermal images for nighttime image enhancement. We leverage self-attention networks for feature extraction and a cross-attention mechanism for fusion to effectively integrate information from both modalities. To support research in this domain, we introduce the Visible-Thermal Image Enhancement Evaluation (V-TIEE) dataset, comprising 50 co-located visible and thermal images captured under diverse nighttime conditions. Extensive evaluations on the publicly available LLVIP dataset and our V-TIEE dataset demonstrate that RT-X Net outperforms state-of-the-art methods in low-light image enhancement. The code and the V-TIEE can be found here https://github.com/jhakrraman/rt-xnet. |
| title | RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.24705 |