DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916314197524480 |
|---|---|
| author | Dong, Wei Zhou, Han Wang, Ruiyi Liu, Xiaohong Zhai, Guangtao Chen, Jun |
| author_facet | Dong, Wei Zhou, Han Wang, Ruiyi Liu, Xiaohong Zhai, Guangtao Chen, Jun |
| contents | Image dehazing, a pivotal task in low-level vision, aims to restore the visibility and detail from hazy images. Many deep learning methods with powerful representation learning capability demonstrate advanced performance on non-homogeneous dehazing, however, these methods usually struggle with processing high-resolution images (e.g., $4000 \times 6000$) due to their heavy computational demands. To address these challenges, we introduce an innovative non-homogeneous Dehazing method via Deformable Convolutional Transformer-like architecture (DehazeDCT). Specifically, we first design a transformer-like network based on deformable convolution v4, which offers long-range dependency and adaptive spatial aggregation capabilities and demonstrates faster convergence and forward speed. Furthermore, we leverage a lightweight Retinex-inspired transformer to achieve color correction and structure refinement. Extensive experiment results and highly competitive performance of our method in NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge, ranking second among all 16 submissions, demonstrate the superior capability of our proposed method. The code is available: https://github.com/movingforward100/Dehazing_R. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05169 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer Dong, Wei Zhou, Han Wang, Ruiyi Liu, Xiaohong Zhai, Guangtao Chen, Jun Computer Vision and Pattern Recognition Image dehazing, a pivotal task in low-level vision, aims to restore the visibility and detail from hazy images. Many deep learning methods with powerful representation learning capability demonstrate advanced performance on non-homogeneous dehazing, however, these methods usually struggle with processing high-resolution images (e.g., $4000 \times 6000$) due to their heavy computational demands. To address these challenges, we introduce an innovative non-homogeneous Dehazing method via Deformable Convolutional Transformer-like architecture (DehazeDCT). Specifically, we first design a transformer-like network based on deformable convolution v4, which offers long-range dependency and adaptive spatial aggregation capabilities and demonstrates faster convergence and forward speed. Furthermore, we leverage a lightweight Retinex-inspired transformer to achieve color correction and structure refinement. Extensive experiment results and highly competitive performance of our method in NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge, ranking second among all 16 submissions, demonstrate the superior capability of our proposed method. The code is available: https://github.com/movingforward100/Dehazing_R. |
| title | DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.05169 |