DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer

TL;DR

DehazeDCT introduces a deformable convolutional transformer architecture for efficient non-homogeneous image dehazing, achieving high performance on high-resolution images with faster convergence and competitive results.

Contribution

The paper proposes a novel deformable convolutional transformer-based network for non-homogeneous dehazing, addressing high computational demands and improving processing speed and accuracy.

Findings

Achieved second place in NTIRE 2024 dehazing challenge.

Demonstrated faster convergence and processing speed.

Provided superior dehazing performance on high-resolution images.

Abstract

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.