Single Image Dehazing via Multi-scale Convolutional Neural Networks

By Wenqi Ren, Sibo Liu, Hua Zhang, Jin-shan Pan, Xiaochun Cao, Ming-Hsuan Yang. European Conference on Computer Vision, 2016

1,713 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/392e419efe21b6e2cc1125f27482d22bf3c677be

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

Image Dehazing Transformer with Transmission-Aware 3D Position Embedding (2022, positive): “With the learning capability of CNNs, CNN-based dehazing networks have achieved impressive performance by either estimating the imaging model’s parameters [25] or directly learning the haze-free counterpart [20].”
Vision Transformers for Single Image Dehazing (2022, background): “DehazeNet [8] and MSCNN [9] are the pioneers in applying CNNs for image dehazing.”
DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks (2017, background): “In the context of CNNs, this is equivalent to using one additional convolutional layer with a ﬁxed Gaussian kernel followed by the mean squared error (MSE) function.”
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration (2020, background): “[33] introduced a multi-scale convolutional neural network for image dehazing and achieved state-of-the-art performance.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, methodology): “We also try three state-of-the-art dehazing approaches: (a) AOD-Net7 [8]; (b) Multi-Scale Convolutional Neural Network (MSCNN)8 [7]; (c) Densely Connected Pyramid Dehazing Network (DCPDN)9 [149].”
Removing Rain from Single Images via a Deep Detail Network (2017, background): “The deep CNN has not only achieved success on high-level vision tasks [12, 13] but has also been extended to problems such as image denoising [34, 36], super-resolution [7, 19], reducing artifacts of compression [8], image inpainting [26] and image dehazing [27].”
Enhanced Pix2pix Dehazing Network (2019, methodology): “Some methods utilize the deep convolutional neural network to estimate the transmission map [3] [15], some employ the deep convolutional neural network to jointly estimate the atmospheric light and”
Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, methodology): “Not surprisingly, although they do not introduce additional distortions, the learning-based approaches of Ren et al [21] and Cai et al [20], trained using synthetic hazy dataset, are not able to remove the hazy (white) appearance.”
MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, background): “As we all know, the effectiveness of deeper structures for low-level image tasks is found not as apparent as that shown in high-level tasks [3, 25].”
An Underwater Image Enhancement Benchmark Dataset and Beyond (2019, background): “, DCP [35] and MSCNN [66]), and 1 commercial application for enhancing underwater images (i.”
Benchmarking Single-Image Dehazing and Beyond (2017, methodology): “DCP [9] FVR [10] BCCR [11] GRM [12] CAP [13] NLD [14] DehazeNet [15] MSCNN [16] AOD-Net [17] PSNR 16.”
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (2018, background): “Convolutional networks have been recently used for dehazing [26], [27], and also for underwater restoration [28].”
FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing (2020, methodology): “We utilize the method in MegaDepth (Li and Snavely 2018) to generate the depths of image scenes and adopt similar ways in MSCNN (Ren et al. 2016) to synthesize the training hazy images.”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, methodology): “RESIDE dataset We evaluate the proposed algorithm on the SOTS data from the RESIDE dataset (Li et al. 2018) against the state-of-the-artmethods (He et al. 2011;Meng et al. 2013; Berman et al. 2016; Cai et al. 2016; Li et al. 2017; Ren et al. 2016).”
Cooperative Semantic Segmentation and Image Restoration in Adverse Environmental Conditions (2019, background): “, DCP [13], NLID [2] and MSCNN [33].”
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing (2018, methodology): “Single image dehazing approaches are divided into prior information-based methods [3,5,12,16,20,32] and learning based methods [10, 24,30,34,35].”
Effects of Image Degradations to CNN-based Image Classification (2018, background): “As discussed earlier, for many kinds of image degradations, many researches have been conducted to remove/reduce the degradation to restore the underlying clear images [15], [16], [17], [18], [19], [20], [21], [22], [25], [37], [38], [40], [42], [44], [45].”
Fast Image Processing with Fully-Convolutional Networks (2017, methodology): “Deep networks have been used for denoising [39, 11, 3], super-resolution [10, 19, 40, 42, 41, 48, 50], deblurring [74], restoration of images corrupted by dirt or rain [22], example-based non-photorealistic stylization [30, 70, 40], joint image filtering [49], dehazing [64], and demosaicking [31].”