Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal

  title={Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal},
  author={Jifeng Wang and Xiang Li and Le Hui and Jian Yang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  • Jifeng WangXiang Li Jian Yang
  • Published 7 December 2017
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Understanding shadows from a single image consists of two types of task in previous studies, containing shadow detection and shadow removal. [] Key Method Our framework is based on a novel STacked Conditional Generative Adversarial Network (ST-CGAN), which is composed of two stacked CGANs, each with a generator and a discriminator. Specifically, a shadow image is fed into the first generator which produces a shadow detection mask.

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

An attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image that outperforms the state-of-the-art methods, especially in detail of recovering shadow areas.

RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal

A general and novel framework RIS-GAN which explores residual and illumination with Generative Adversarial Networks for shadow removal and achieves the superior performance to state-of-the-arts, although it has no particular shadow-aware components designed in its generators.

TC-ShadowGAN: A Target-Consistency Generative Adversarial Network for Unpaired Shadow Removal

This work develops a sim-ple yet effective target-consistency generative adversarial net-work (TC-ShadowGAN) for the task of unpaired shadow re-moval without any additional label for supervision.

Image Shadow Removal Based on Generative Adversarial Networks

An image shadow removal method based on generative adversarial networks that is trained in unsupervised fashion which means it does not depend on time-consuming data collection and data labeling, and produces better results compared to the existing approach in the field.

Deep Multi-task Learning for Shadow Detection and Removal

A multi-task adversarial generative networks (mtGAN) that can detect and remove shadows simultaneously simultaneously is proposed and can achieve shadow detection and removal tasks better than existing methods.

Mask-ShadowGAN: Learning to Remove Shadows From Unpaired Data

Mask-ShadowGAN is a new deep framework that automatically learns to produce a shadow mask from the input shadow image and then takes the mask to guide the shadow generation via re-formulated cycle-consistency constraints, to maximize the overall performance.

Throwaway Shadows Using Parallel Encoders Generative Adversarial Network

This work proposes a novel generative adversarial network (GAN) based image-to-image translation approach for shadow removal in face images and finds that this combination in the generator results in learning an incorporated semantic structure and in disentangling visual discrepancies problems under the shadow area.

Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network

A simple yet efficient target-consistency generative adversarial network (TC-GAN) for the shadow removal task in the unsupervised manner that achieves comparable performance with supervised shadow removal methods.

Bijective Mapping Network for Shadow Removal

A new Bijective Mapping Network (BMNet), which couples the learning procedures of shadow removal and shadow generation in a unified parameter-shared framework and outperforms the state-of-the-art method in de-shadowing performance, while only using its 0.25% network parameters and 6.

V-ShadowGAN: generative adversarial networks for removing and generating shadows associated with vehicles based on unpaired data

Abstract. We propose a method to change the shadows cast by vehicles based on unpaired data, which is used to solve the problem of insufficient datasets for target detection in autonomous driving



Shadow Detection with Conditional Generative Adversarial Networks

This work introduces scGAN, a novel extension of conditional Generative Adversarial Networks (GAN) tailored for the challenging problem of shadow detection in images, and introduces an additional sensitivity parameter to the generator of a conditional GAN.

DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal

An automatic and end-to-end deep neural network (DeshadowNet) to tackle shadow removal problems in a unified manner and shows that the proposed method performs favorably against several state-of-the-art methods.

Stacked Generative Adversarial Networks

A novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network, which is able to generate images of much higher quality than GANs without stacking.

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

The architecture introduced in this paper learns a mapping function G : X 7→ Y using an adversarial loss such thatG(X) cannot be distinguished from Y , whereX and Y are images belonging to two

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

This paper proposes Stacked Generative Adversarial Networks (StackGAN) to generate 256 photo-realistic images conditioned on text descriptions and introduces a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold.

Automatic Shadow Detection and Removal from a Single Image

A framework to automatically detect and remove shadows in real world scenes from a single image using multiple convolutional deep neural networks (ConvNets) based on a novel model which accurately models the shadow generation process in the umbra and penumbra regions.

Image-to-Image Translation with Conditional Adversarial Networks

Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

This work presents an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples, and introduces a cycle consistency loss to push F(G(X)) ≈ X (and vice versa).

Context Encoders: Feature Learning by Inpainting

It is found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures, and can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.