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

Ding, Bin; Long, Chengjiang; Zhang, Ling; Xiao, Chunxia

doi:10.1109/iccv.2019.01031

Cited by 151 publications

(77 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, learning-based approaches have demonstrated a significant improvement on general-purpose shadow detection and manipulation [Cun et al 2020;Ding et al 2019;Hu et al 2019Khan et al 2015;Zheng et al 2019;. However, like all learned techniques, such approaches are limited by the nature of their training data.…”

Section: Related Workmentioning

confidence: 99%

Portrait shadow manipulation

et al. 2020

View full text Add to dashboard Cite

Fig. 1. The results of our portrait enhancement method on real-world portrait photographs. Casual portrait photographs often suffer from undesirable shadows, particularly foreign shadows cast by external objects, and dark facial shadows cast by the face upon itself under harsh illumination. We propose an automated technique for enhancing these poorly-lit portrait photographs by removing unwanted foreign shadows, reducing harsh facial shadows, and adding synthetic fill lights. Casually-taken portrait photographs often suffer from unflattering lighting and shadowing because of suboptimal conditions in the environment. Aesthetic qualities such as the position and softness of shadows and the lighting ratio between the bright and dark parts of the face are frequently determined by the constraints of the environment rather than by the photographer. Professionals address this issue by adding light shaping tools such as scrims, bounce cards, and flashes. In this paper, we present a computational approach that gives casual photographers some of this control, thereby

show abstract

Section: Related Workmentioning

confidence: 99%

Portrait shadow manipulation

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Wei et al (Wei et al 2019) proposed a two-stage generative adversarial network for shadow inpainting and removal with slice convolutions. Ding et al (Ding et al 2019) proposed an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadow with multiple steps. Different from existing methods, our proposed RIS-GAN makes full use of the explored negative residual image and the inverse illumination map for generating more accurate shadow-removal results.…”

Section: Related Workmentioning

confidence: 99%

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

Zhang

Long

Zhang

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

Residual images and illumination estimation have been proved very helpful in image enhancement. In this paper, we propose a general and novel framework RIS-GAN which explores residual and illumination with Generative Adversarial Networks for shadow removal. Combined with the coarse shadow-removal image, the estimated negative residual images and inverse illumination maps can be used to generate indirect shadow-removal images to refine the coarse shadow-removal result to the fine shadow-free image in a coarse-to-fine fashion. Three discriminators are designed to distinguish whether the predicted negative residual images, shadow-removal images, and the inverse illumination maps are real or fake jointly compared with the corresponding ground-truth information. To our best knowledge, we are the first one to explore residual and illumination for shadow removal. We evaluate our proposed method on two benchmark datasets, i.e., SRD and ISTD, and the extensive experiments demonstrate that our proposed method achieves the superior performance to state-of-the-arts, although we have no particular shadow-aware components designed in our generators.

show abstract

“…Recently, GAN [7] models have achieved great success in various computer vision tasks, including image translation [8,9], shadow removal [10], and realistic super-resolution [11,12], etc. The vanilla GAN framework consists of a generator and a discriminator.…”

Section: A Generative Adversarial Network (Gan)mentioning

confidence: 99%

User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach

2020

View full text Add to dashboard Cite

Image completion models based on deep neural networks have been a research hot spot in computer vision. However, most of the previous methods focus on natural images, such as faces and landscapes. In this paper, we propose a novel image completion model for a special set of artificial ancient Chinese paintings to address this limitation. Specifically, we integrate three complements: the Wasserstein Generative Adversarial Networks (WGAN), Perceptual loss, and Mean Squared Error (MSE) to train the model robustly. We propose a unique generator which can not only pay more attention to complete the details of ancient Chinese paintings but also can provide the synthesized lines to help artists to analyze paintings conveniently. Additionally, we also allow a user to supply a structure hint to guide our model to complete Chinese paintings according to his/her preference. Extensive experiments firmly demonstrate the effectiveness of our approach to complete ancient Chinese paintings and remove abnormal color blocks from them.

show abstract

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

Cited by 151 publications

References 58 publications

Portrait shadow manipulation

Portrait shadow manipulation

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

User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach

Contact Info

Product

Resources

About