WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909338280394752 |
|---|---|
| author | Appiah, Divine Joseph Guan, Donghai Kasule, Abdul Nasser Wei, Mingqiang |
| author_facet | Appiah, Divine Joseph Guan, Donghai Kasule, Abdul Nasser Wei, Mingqiang |
| contents | Images captured in hazy outdoor conditions often suffer from colour distortion, low contrast, and loss of detail, which impair high-level vision tasks. Single image dehazing is essential for applications such as autonomous driving and surveillance, with the aim of restoring image clarity. In this work, we propose WTCL-Dehaze an enhanced semi-supervised dehazing network that integrates Contrastive Loss and Discrete Wavelet Transform (DWT). We incorporate contrastive regularization to enhance feature representation by contrasting hazy and clear image pairs. Additionally, we utilize DWT for multi-scale feature extraction, effectively capturing high-frequency details and global structures. Our approach leverages both labelled and unlabelled data to mitigate the domain gap and improve generalization. The model is trained on a combination of synthetic and real-world datasets, ensuring robust performance across different scenarios. Extensive experiments demonstrate that our proposed algorithm achieves superior performance and improved robustness compared to state-of-the-art single image dehazing methods on both benchmark datasets and real-world images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04762 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning Appiah, Divine Joseph Guan, Donghai Kasule, Abdul Nasser Wei, Mingqiang Computer Vision and Pattern Recognition Images captured in hazy outdoor conditions often suffer from colour distortion, low contrast, and loss of detail, which impair high-level vision tasks. Single image dehazing is essential for applications such as autonomous driving and surveillance, with the aim of restoring image clarity. In this work, we propose WTCL-Dehaze an enhanced semi-supervised dehazing network that integrates Contrastive Loss and Discrete Wavelet Transform (DWT). We incorporate contrastive regularization to enhance feature representation by contrasting hazy and clear image pairs. Additionally, we utilize DWT for multi-scale feature extraction, effectively capturing high-frequency details and global structures. Our approach leverages both labelled and unlabelled data to mitigate the domain gap and improve generalization. The model is trained on a combination of synthetic and real-world datasets, ensuring robust performance across different scenarios. Extensive experiments demonstrate that our proposed algorithm achieves superior performance and improved robustness compared to state-of-the-art single image dehazing methods on both benchmark datasets and real-world images. |
| title | WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.04762 |