AOD-Net: All-in-One Dehazing Network

By Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng. IEEE International Conference on Computer Vision, 2017

2,090 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/867f1a262a704ef4cabe84899310370182dd598f

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

Citations in the corpus

Gated Context Aggregation Network for Image Dehazing and Deraining (2018, methodology): “[22] reformulates the atmospheric scattering model to predict the ﬁnal clean image through a light-weight CNN. [32] creates three different derived input images from the original hazy image and fuses the dehazed results out of these derived inputs.”
Depth-Attentional Features for Single-Image Rain Removal (2019, methodology): “Moreover, since our network is also able to remove fog in the rain images, we further compared our method with two state-of-the-art haze removal methods, i.e., DCPDN [49] and AOD-Net [27]; they are both deep-learning-based methods, so we re-trained their models for rain removal.”
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration (2019, positive): “ule)) for haze removal. Table 6: Results for haze removal on Dehaze-TestA dataset and RESIDE-SOTS dataset. Dehaze-TestA He et al. [12] 0.8642 Zhu et al. [58] 0.8567 Berman et al. [3] 0.7959 Li et al. [22] 0.8842 Zhang et al. [53] 0.9560 DuRN-US (ours) 0.9827 RESIDE-SOTS Berman et al. [3] 17.27 / 0.7”
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].”
Enhanced Pix2pix Dehazing Network (2019, methodology): “Input DCP [7] DehazeNet [3] AOD-Net [10] DCPDN [21] GFN [16] Ours GT Figure 5.”
Single Image Dehazing via Conditional Generative Adversarial Network (2018, methodology): “(e) Ren [7] (f) Li [5] (g) Meng [6] (h) Ours Figure 9: Visual comparison on real image.”
Artificial intelligence in the creative industries: a review (2020, background): “performs best in terms of perceptual loss, MSCNN [149] oers the best subjective quality and superior detection 23 AI in the Creative Industries: A Review performance on real hazy images, and AOD-Net [145] is the most ecient. A related application is underwater photography [144] as commonly used in n”
Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather (2019, background): “These priors are either hand-crafted [25] and used for depth and transmission estimation separately, or they are learned jointly as part of trainable end-to-end models [37, 31, 72].”
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.”
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing (2019, methodology): “Moreover, except for AOD-Net and GFN, these methods all follow the same strategy of ﬁrst estimating the transmission map and the atmosphere light then leveraging the atmo-( sphere scattering model to compute the dehazed image.”
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing (2019, background): “(Li et al. 2017) AOD-Net directly generates a clean image through a light-weight CNN.”
MAXIM: Multi-Axis MLP for Image Processing (2022, positive): “For instance, UNet [78] has incubated many successful encoder-decoder designs [19, 36, 108] for image restoration that improve on earlier single-scale feature processing models [44, 117].”
EnlightenGAN: Deep Light Enhancement Without Paired Supervision (2019, background): “l-world generalization. 4.5. Pre-Processing for Improving Classiﬁcation Image enhancement as pre-processing for improving subsequent high-level vision tasks has recently received increasing attention [28,49,50], with a number of benchmarking efforts [47,51,52]. We investigate the impact of light enh”
Contrastive Learning for Compact Single Image Dehazing (2021, methodology): “DehazeNet [5] and AOD-Net [25]), and hazy-to-clear image translation based methods (e.”
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (2021, neutral): “Some priorbased methods (Li et al. 2017; Huang, Le, and Jaw 2020) jointly perform image enhancement and detection to attenuate the interference of adverse weather-specific information.”
Domain Adaptation for Image Dehazing (2020, methodology): “We evaluate the proposed method against the following state-of-the-art approaches: DCP [9], MSCNN [26], DehazeNet [4], NLD [2], AOD-Net [12],”
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (2020, background): “(a1) Ground-truth (b1) Hazy input (c1) DCP [3] (d1) AOD [6]”
Single Image Deraining: A Comprehensive Benchmark Analysis (2019, methodology): “The Rain and mist (T) set is synthesized by first adding haze using the atmospheric scattering model: for each clean image, we estimate depth using the algorithm in [35, 36] as recommended by [37], set different atmospheric lights A by choosing each channel uniformly randomly between [0.”
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].”