DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer
This work addresses computational inefficiency in dehazing for high-resolution images, which is incremental as it builds on existing deep learning approaches.
The paper tackles non-homogeneous image dehazing for high-resolution images by introducing DehazeDCT, a method combining deformable convolution and transformer-like architectures, achieving second place in the NTIRE 2024 challenge among 16 submissions.
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.