T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing

Zheng, Lirong; Li, Yanshan; Zhang, Kaihao; Luo, Wenhan

doi:10.1109/tmm.2022.3214780

Cited by 20 publications

(4 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method is compared with 10 state-of-the-art methods: DehazeNet 16 (2016), AOD-Net 17 (2017), GFN 19 (2018), DCPDN 18 (2018), EPDN 20 (2019), Y-Net 22 (2020), Domain Adaptation Dehazing Network (DADN) 53 (2020), Stack T-Net 54 (2021), FSAD-Net 55 (2022), and GP2P+ 56 (2022).…”

Section: Methodsmentioning

confidence: 99%

Retinex decomposition and fusion dehazing network

et al. 2023

View full text Add to dashboard Cite

Image dehazing has been widely used in vision-based fields, such as detection, segmentation, traffic monitoring, and automated vehicle system. However, most of the existing endto-end dehazing networks are fully data driven without physical constraints or prior information guidance, leading to difficulties in exploring latent structures and statistical characteristics of hazy images. We propose a novel Retinex decomposition-fusion dehazing network consisting of a dual-branch decomposition module and a fusion optimization module. Different from existing solutions, we decompose the clear images in the commonly used RESIDE dataset based on Retinex theory to construct the clear illumination map and reflection map datasets to drive the network training, equivalently imposing reasonable constraints on the network and achieving impressive dehazing performances. The dual-branch decomposition module is developed to estimate the illumination map and the reflection map, respectively. The illumination map mainly contains the global features of the image, whereas the reflection map reflects the inherent color properties of the image and contains rich details, with which we explore the latent structures and statistical characteristics of hazy images. In addition, the dual-branch structure avoids the error accumulation and information cancellation existing in current methods. Subsequently, the estimated illumination map and reflection map are fused and refined via the fusion optimization module to access the dehazed image. Experiments show that the proposed network has better generalization and visual effects than existing fully data-driven methods and can be applied successfully to real-world scenarios.

show abstract

Section: Methodsmentioning

confidence: 99%

Retinex decomposition and fusion dehazing network

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In addition, considering that the features of different scales may not be equally important, we use a simple weighted attention fusion strategy to achieve feature fusion from the different row and column dimensions. Inspired by [79,62], we first generate two trainable weights for different features, where each parameter is an n-dimensional vector (n is the channels of feature). We add these weighted features to derive the fusion features.…”

Section: Gridformer Architecturementioning

confidence: 99%

“…Previous works [18,78,36,75,79] have shown that using dense connections has many advantages, mitigating the vanishing gradient problem, encouraging feature reuse and enhancing information propagation. Accordingly, we propose to design the transformer with dense connections to build the basic GridFormer layers.…”

Section: Residual Dense Transformer Blockmentioning

confidence: 99%

“…For example, using the pre-trained strategy [6] or contrastive learning technique [64] on our GridFormer can further explore its performance potential. In addition, we fuse multi-scale features with simple weighted attention [79,62]. We can improve this fusion by designing special modules using sophisticated attention mechanisms [46,56].…”

Section: Limitations and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Residual Haze Network for Image Dehazing and Deraining

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Image dehazing on a hazy image aims to remove the haze and make the image scene clear, which attracts more and more research interests in recent years. Most existing image dehazing methods use a classic atmospheric scattering model and natural image priors to remove the image haze. In this paper, we propose an end-to-end image dehazing model termed as DRHNet (Deep Residual Haze Network), which restores the haze-free image by subtracting the learned negative residual map from the hazy image. Specifically, DRHNet proposes a context-aware feature extraction module to aggregate the contextual information effectively. Furthermore, it proposes a novel nonlinear activation function termed as RPReLU (Reverse Parametric Rectified Linear Unit) to improve its representation ability and to accelerate its convergence. Extensive experiments demonstrate that DRHNet outperforms state-of-the-art methods both quantitatively and qualitatively. In addition, experiments on image deraining task show that DRHNet can also serve for image deraining. INDEX TERMS Image dehazing, image deraining, negative residual map, context-aware feature extraction, reverse parametric rectified linear unit (RPReLU).

show abstract