Parallel Cross Strip Attention Network for Single Image Dehazing
This work addresses the problem of restoring clear images from hazy inputs for applications in computer vision, though it is incremental as it builds on existing attention-based methods.
The paper tackles single image dehazing by proposing a Parallel Stripe Cross Attention network with a multi-scale strategy to capture long-range dependencies and adapt to varying blur sizes, achieving improved performance on benchmarks like SOTS and Haze4K with PSNR gains of up to 2.5 dB.
The objective of single image dehazing is to restore hazy images and produce clear, high-quality visuals. Traditional convolutional models struggle with long-range dependencies due to their limited receptive field size. While Transformers excel at capturing such dependencies, their quadratic computational complexity in relation to feature map resolution makes them less suitable for pixel-to-pixel dense prediction tasks. Moreover, fixed kernels or tokens in most models do not adapt well to varying blur sizes, resulting in suboptimal dehazing performance. In this study, we introduce a novel dehazing network based on Parallel Stripe Cross Attention (PCSA) with a multi-scale strategy. PCSA efficiently integrates long-range dependencies by simultaneously capturing horizontal and vertical relationships, allowing each pixel to capture contextual cues from an expanded spatial domain. To handle different sizes and shapes of blurs flexibly, We employs a channel-wise design with varying convolutional kernel sizes and strip lengths in each PCSA to capture context information at different scales.Additionally, we incorporate a softmax-based adaptive weighting mechanism within PCSA to prioritize and leverage more critical features.