Beyond Night Visibility: Adaptive Multi-Scale Fusion of Infrared and Visible Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911787852496896 |
|---|---|
| author | Pei, Shufan Lin, Junhong Liu, Wenxi Zhao, Tiesong Lin, Chia-Wen |
| author_facet | Pei, Shufan Lin, Junhong Liu, Wenxi Zhao, Tiesong Lin, Chia-Wen |
| contents | In addition to low light, night images suffer degradation from light effects (e.g., glare, floodlight, etc). However, existing nighttime visibility enhancement methods generally focus on low-light regions, which neglects, or even amplifies the light effects. To address this issue, we propose an Adaptive Multi-scale Fusion network (AMFusion) with infrared and visible images, which designs fusion rules according to different illumination regions. First, we separately fuse spatial and semantic features from infrared and visible images, where the former are used for the adjustment of light distribution and the latter are used for the improvement of detection accuracy. Thereby, we obtain an image free of low light and light effects, which improves the performance of nighttime object detection. Second, we utilize detection features extracted by a pre-trained backbone that guide the fusion of semantic features. Hereby, we design a Detection-guided Semantic Fusion Module (DSFM) to bridge the domain gap between detection and semantic features. Third, we propose a new illumination loss to constrain fusion image with normal light intensity. Experimental results demonstrate the superiority of AMFusion with better visual quality and detection accuracy. The source code will be released after the peer review process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01083 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Night Visibility: Adaptive Multi-Scale Fusion of Infrared and Visible Images Pei, Shufan Lin, Junhong Liu, Wenxi Zhao, Tiesong Lin, Chia-Wen Computer Vision and Pattern Recognition In addition to low light, night images suffer degradation from light effects (e.g., glare, floodlight, etc). However, existing nighttime visibility enhancement methods generally focus on low-light regions, which neglects, or even amplifies the light effects. To address this issue, we propose an Adaptive Multi-scale Fusion network (AMFusion) with infrared and visible images, which designs fusion rules according to different illumination regions. First, we separately fuse spatial and semantic features from infrared and visible images, where the former are used for the adjustment of light distribution and the latter are used for the improvement of detection accuracy. Thereby, we obtain an image free of low light and light effects, which improves the performance of nighttime object detection. Second, we utilize detection features extracted by a pre-trained backbone that guide the fusion of semantic features. Hereby, we design a Detection-guided Semantic Fusion Module (DSFM) to bridge the domain gap between detection and semantic features. Third, we propose a new illumination loss to constrain fusion image with normal light intensity. Experimental results demonstrate the superiority of AMFusion with better visual quality and detection accuracy. The source code will be released after the peer review process. |
| title | Beyond Night Visibility: Adaptive Multi-Scale Fusion of Infrared and Visible Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01083 |