LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911130483425280 |
|---|---|
| author | Yi, Xunpeng Zhang, Yibing Xiang, Xinyu Yan, Qinglong Xu, Han Ma, Jiayi |
| author_facet | Yi, Xunpeng Zhang, Yibing Xiang, Xinyu Yan, Qinglong Xu, Han Ma, Jiayi |
| contents | Current advanced research on infrared and visible image fusion primarily focuses on improving fusion performance, often neglecting the applicability on real-time fusion devices. In this paper, we propose a novel approach that towards extremely fast fusion via distillation to learnable lookup tables specifically designed for image fusion, termed as LUT-Fuse. Firstly, we develop a look-up table structure that utilizing low-order approximation encoding and high-level joint contextual scene encoding, which is well-suited for multi-modal fusion. Moreover, given the lack of ground truth in multi-modal image fusion, we naturally proposed the efficient LUT distillation strategy instead of traditional quantization LUT methods. By integrating the performance of the multi-modal fusion network (MM-Net) into the MM-LUT model, our method achieves significant breakthroughs in efficiency and performance. It typically requires less than one-tenth of the time compared to the current lightweight SOTA fusion algorithms, ensuring high operational speed across various scenarios, even in low-power mobile devices. Extensive experiments validate the superiority, reliability, and stability of our fusion approach. The code is available at https://github.com/zyb5/LUT-Fuse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00346 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables Yi, Xunpeng Zhang, Yibing Xiang, Xinyu Yan, Qinglong Xu, Han Ma, Jiayi Computer Vision and Pattern Recognition Current advanced research on infrared and visible image fusion primarily focuses on improving fusion performance, often neglecting the applicability on real-time fusion devices. In this paper, we propose a novel approach that towards extremely fast fusion via distillation to learnable lookup tables specifically designed for image fusion, termed as LUT-Fuse. Firstly, we develop a look-up table structure that utilizing low-order approximation encoding and high-level joint contextual scene encoding, which is well-suited for multi-modal fusion. Moreover, given the lack of ground truth in multi-modal image fusion, we naturally proposed the efficient LUT distillation strategy instead of traditional quantization LUT methods. By integrating the performance of the multi-modal fusion network (MM-Net) into the MM-LUT model, our method achieves significant breakthroughs in efficiency and performance. It typically requires less than one-tenth of the time compared to the current lightweight SOTA fusion algorithms, ensuring high operational speed across various scenarios, even in low-power mobile devices. Extensive experiments validate the superiority, reliability, and stability of our fusion approach. The code is available at https://github.com/zyb5/LUT-Fuse. |
| title | LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.00346 |