Multi-Scale Boosted Dehazing Network With Dense Feature Fusion

By Hang Dong, Jin-shan Pan, Lei Xiang, Zhe Hu, Xinyi Zhang, Fei Wang, Ming-Hsuan Yang. Computer Vision and Pattern Recognition, 2020

1,022 citations recorded by the source corpus.

In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we show that they are suitable for the dehazing problem. By incorporating the Strengthen-Operate-Subtract boosting strategy in the decoder of the proposed model, we develop a simple yet effective boosted decoder to progressively restore the haze-free image. To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme. We show that the dense feature fusion module can simultaneously remedy the missing spatial information from high-resolution features and exploit the non-adjacent features. Extensive evaluations demonstrate that the proposed model performs favorably against the state-of-the-art approaches on the benchmark datasets as well as real-world hazy images.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/57f2019325ce70212dd56d59b413564f98e00664

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Vision Transformers for Single Image Dehazing (2022, methodology): “And current methods [13], [14], [15], [16], [17], [18], [19], [20], [21] prefer to predict the latent haze-free image or the residuals of the haze-free image versus the hazy image since it tends to achieve better perfor-”
Contrastive Learning for Compact Single Image Dehazing (2021, methodology): “Previous works [35, 30, 34, 23, 10, 42] usually employ the fixed grid kernel (e.”
UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space (2021, background): “Unlike other low-level vision tasks such as image super-resolution [35], image denoising [36], image deblurring [37] and image de-hazing [38], which can use plenty of synthetic degraded images and high-quality counterparts for training, it is difﬁcult to synthesize realistic underwater images for…”
DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention (2023, methodology): “We observe that fusing the features from the encoder part with that from the decoder part is an effective trick in dehazing and other low-level vision tasks [6], [10], [38], [39].”
MAXIM: Multi-Axis MLP for Image Processing (2022, background): “Recently, multi-stage networks [15, 33, 108, 110] have attained promising results relative to the aforementioned single-stage models on the challenging deblurring and deraining tasks [22, 33, 108].”
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions (2021, methodology): “Note that from our experiments we found MSBDN to be the best performing network for dehazing.”
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (2021, neutral): “Another approach is to dilute the inﬂuence of weather-speciﬁc information by preprocessing the image with existing methods such as image defogging (Hang et al. 2020; Liu et al. 2019) and image enhancement (Guo et al. 2020).”
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors (2021, background): “(d) FFA-Net [11] (e) MSBDN [3] (f) SSLD [9]”