A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation

Le, Hieu Van; Vicente, Tomás F. Yago; Nguyen, Vu; Hoai, Minh; Samaras, Dimitris

doi:10.1007/978-3-030-01216-8_41

Cited by 99 publications

(75 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such an algorithm can be considered as a pre-processing step to improve the performance of a wide range of algorithms including those currently being used for OCT image segmentation, denoising, and classi cation. 15…”

Section: Discussionmentioning

confidence: 99%

DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images

Cheong

Devalla

Pham

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Purpose: To remove retinal shadows from optical coherence tomography (OCT) images of the optic nerve head (ONH). Methods: 2328 OCT images acquired through the center of the ONH using a Spectralis OCT machine for both eyes of 13 subjects were used to train a generative adversarial network (GAN) using a custom loss function.Image quality was assessed qualitatively (for artifacts) and quantitatively using the intralayer contrast a measure of shadow visibility ranging from 0 (shadow-free) to 1 (strong shadow) and compared to compensated images. is was computed in the Retinal Nerve Fiber Layer (RNFL), the Inner Plexiform Layer (IPL), the Photoreceptor layer (PR) and the Retinal Pigment Epithelium (RPE) layers. Results: Output images had improved intralayer contrast in all ONH tissue layers. On average the intralayer contrast decreased by 33.7 ± 6.81%, 28.8 ± 10.4%, 35.9 ± 13.0%, and 43.0 ± 19.5% for the RNFL, IPL, PR, and RPE layers respectively, indicating successful shadow removal across all depths. is compared to 70.3 ± 22.7%, 33.9 ± 11.5%, 47.0 ± 11.2%, 26.7 ± 19.0% for compensation. Output images were also free from artifacts commonly observed with compensation. Conclusions: DeshadowGAN signi cantly corrected blood vessel shadows in OCT images of the ONH. Our algorithm may be considered as a pre-processing step to improve the performance of a wide range of algorithms including those currently being used for OCT image segmentation, denoising, and classi cation. Translational Relevance: DeshadowGAN could be integrated to existing OCT devices to improve the diagnosis and prognosis of ocular pathologies.

show abstract

Section: Discussionmentioning

confidence: 99%

DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images

Cheong

Devalla

Pham

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…we visualize some results in Figure 7. As we can see, (1) traditional methods Guo [12] and Zhang [60] are not able to effectively detect slender shadows in the image; (2) among all deep learning methods, comparing with ST-CGAN [54], DSC [16], A+D Net [27] and BDRAR [63], our proposed ARGAN is able to detect more accurate shadow regions and even more close to our human observation. Figure 8 presents two more shadow images with more complex scenes.…”

Section: Performance Comparison On Shadow Detectionmentioning

confidence: 88%

“…Shadow detection methods involve traditional methods, using user interactions [11,60,6] and hand-crafted features [26,12,52], and recent deep learning methods [24,53,41,17,27,63] for automatic shadow detection. To specify, Khan et al [24] detected the shadow by combining the boundary and region ConvNets in the CRF model.…”

Section: Related Workmentioning

confidence: 99%

ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal

Ding

Long

Zhang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

141

View full text Add to dashboard Cite

In this paper we propose an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image. The generator consists of multiple progressive steps. At each step a shadow attention detector is firstly exploited to generate an attention map which specifies shadow regions in the input image.Given the attention map, a negative residual by a shadow remover encoder will recover a shadow-lighter or even a shadow-free image. A discriminator is designed to classify whether the output image in the last progressive step is real or fake. Moreover, ARGAN is suitable to be trained with a semi-supervised strategy to make full use of sufficient unsupervised data. The experiments on four public datasets have demonstrated that our ARGAN is robust to detect both simple and complex shadows and to produce more realistic shadow removal results. It outperforms the state-of-the-art methods, especially in detail of recovering shadow areas.

show abstract

“…Many deep learning work focus on learning from more easily obtainable, weakly-supervised, or synthetic data [2,19,21,22,29,18,17]. In this section, we show that we can modify shadow effects using our proposed illumination model to generate additional training data.…”

Section: Dataset Augmentation Via Shadow Editingmentioning

confidence: 93%

Shadow Removal via Shadow Image Decomposition

Samaras

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

143

180

View full text Add to dashboard Cite

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects on the images. We train and test our framework on the most challenging shadow removal dataset (ISTD). Compared to the state-ofthe-art method, our model achieves a 40% error reduction in terms of root mean square error (RMSE) for the shadow area, reducing RMSE from 13.3 to 7.9. Moreover, we create an augmented ISTD dataset based on an image decomposition system by modifying the shadow parameters to generate new synthetic shadow images. Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7.4.

show abstract

A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation

Cited by 99 publications

References 33 publications

DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images

DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images

ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal

Shadow Removal via Shadow Image Decomposition

Contact Info

Product

Resources

About