FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915262205263872 |
|---|---|
| author | Shi, Kangbiao Feng, Yixu Hu, Tao Cao, Yu Wu, Peng Liang, Yijin Zhang, Yanning Yan, Qingsen |
| author_facet | Shi, Kangbiao Feng, Yixu Hu, Tao Cao, Yu Wu, Peng Liang, Yijin Zhang, Yanning Yan, Qingsen |
| contents | The advent of Deep Neural Networks (DNNs) has driven remarkable progress in low-light image enhancement (LLIE), with diverse architectures (e.g., CNNs and Transformers) and color spaces (e.g., sRGB, HSV, HVI) yielding impressive results. Recent efforts have sought to leverage the complementary strengths of these paradigms, offering promising solutions to enhance performance across varying degradation scenarios. However, existing fusion strategies are hindered by challenges such as parameter explosion, optimization instability, and feature misalignment, limiting further improvements. To overcome these issues, we introduce FusionNet, a novel multi-model linear fusion framework that operates in parallel to effectively capture global and local features across diverse color spaces. By incorporating a linear fusion strategy underpinned by Hilbert space theoretical guarantees, FusionNet mitigates network collapse and reduces excessive training costs. Our method achieved 1st place in the CVPR2025 NTIRE Low Light Enhancement Challenge. Extensive experiments conducted on synthetic and real-world benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art methods in terms of both quantitative and qualitative results, delivering robust enhancement under diverse low-light conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19295 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement Shi, Kangbiao Feng, Yixu Hu, Tao Cao, Yu Wu, Peng Liang, Yijin Zhang, Yanning Yan, Qingsen Computer Vision and Pattern Recognition The advent of Deep Neural Networks (DNNs) has driven remarkable progress in low-light image enhancement (LLIE), with diverse architectures (e.g., CNNs and Transformers) and color spaces (e.g., sRGB, HSV, HVI) yielding impressive results. Recent efforts have sought to leverage the complementary strengths of these paradigms, offering promising solutions to enhance performance across varying degradation scenarios. However, existing fusion strategies are hindered by challenges such as parameter explosion, optimization instability, and feature misalignment, limiting further improvements. To overcome these issues, we introduce FusionNet, a novel multi-model linear fusion framework that operates in parallel to effectively capture global and local features across diverse color spaces. By incorporating a linear fusion strategy underpinned by Hilbert space theoretical guarantees, FusionNet mitigates network collapse and reduces excessive training costs. Our method achieved 1st place in the CVPR2025 NTIRE Low Light Enhancement Challenge. Extensive experiments conducted on synthetic and real-world benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art methods in terms of both quantitative and qualitative results, delivering robust enhancement under diverse low-light conditions. |
| title | FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19295 |