Robust Image Colorization Using Self Attention Based Progressive Generative Adversarial Network

Sharma, Manoj Kumar; Makwana, Megh; Upadhyay, Avinash; Singh, Ajay Pratap; Badhwar, Anuj; Trivedi, Akkshita; Saini, Anil; Chaudhury, Santanu

doi:10.1109/cvprw.2019.00272

Cited by 11 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the last decade, several methods [24][25][26][27][28][29][30][31] have been introduced for image colorization tasks. Deshpande et al [26] using a variational autoencoder (VAE) to learn a low dimensional embedding of color fields.…”

Section: Image Colorizationmentioning

confidence: 99%

“…Nazeri et al [30] use a conditional Deep Convolutional Generative Adversarial Network (DCGAN) to generalize the process of automatic image colorization. Sharma et al [31] proposed Self-Attention-based Progressive Generative Adversarial Network (RIC-SPGAN) to perform the denoising and colorization of the image. However, these methods mainly focus on colorization of gray-scale images, which are mainly applicable to the restoration of aged or degraded images.…”

Section: Image Colorizationmentioning

confidence: 99%

See 1 more Smart Citation

Colorization of Logo Sketch Based on Conditional Generative Adversarial Networks

Tian

Liu

et al. 2021

Electronics

View full text Add to dashboard Cite

Logo design is a complex process for designers and color plays a very important role in logo design. The automatic colorization of logo sketch is of great value and full of challenges. In this paper, we propose a new logo design method based on Conditional Generative Adversarial Networks, which can output multiple colorful logos only by providing one logo sketch. We improve the traditional U-Net structure, adding channel attention and spatial attention in the process of skip-connection. In addition, the generator consists of parallel attention-based U-Net blocks, which can output multiple logo images. During the model optimization process, a style loss function is proposed to improve the color diversity of the logos. We evaluate our method on the self-built edges2logos dataset and the public edges2shoes dataset. Experimental results show that our method can generate more colorful and realistic logo images based on simple sketches. Compared to the classic networks, the logos generated by our network are also superior in visual effects.

show abstract

Section: Image Colorizationmentioning

confidence: 99%

Section: Image Colorizationmentioning

confidence: 99%

Colorization of Logo Sketch Based on Conditional Generative Adversarial Networks

Tian

Liu

et al. 2021

Electronics

View full text Add to dashboard Cite

show abstract

“…A lot of work has proposed fully automatic colorization [3,10,15,19,28,32,34,42]. Most of it was based on the deep neural network (DNN) [40,41] and achieved high-quality image colorization.…”

Section: Introductionmentioning

confidence: 99%

“…With the development of generative adversarial networks (GANs) [21], Chia et al [5] utilized a GAN to propose style conversion networks that can transfer an image style from another image, which also can be applied to transferring color to a grayscale image, or to synthesize a color image from a grayscale image [10,15,28,32]. The CycleGAN [44], in particular, enables the learning of unpaired datasets by applying cycle-consistency.…”

Section: Introductionmentioning

confidence: 99%

Unpaired medical image colorization using generative adversarial network

Liang

Lee

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

We consider medical image transformation problems where a grayscale image is transformed into a color image. The colorized medical image should have the same features as the input image because extra synthesized features can increase the possibility of diagnostic errors. In this paper, to secure colorized medical images and improve the quality of synthesized images, as well as to leverage unpaired training image data, a colorization network is proposed based on the cycle generative adversarial network (CycleGAN) model, combining a perceptual loss function and a total variation (TV) loss function. Visual comparisons and experimental indicators from the NRMSE, PSNR, and SSIM metrics are used to evaluate the performance of the proposed method. The experimental results show that GAN-based style conversion can be applied to colorization of medical images. As well, the introduction of perceptual loss and TV loss can improve the quality of images produced as a result of colorization better than the result generated by only using the CycleGAN model.

show abstract

“…为了克服 GANs 不稳定性问题, 研究者们通过优化网络结构 [2,4,15,16] 、改变梯度更新方法 [13,17,18] 、修改目标函数 [3, 12, 19∼21] , 以及对判别器实施正则化 [22∼24] 或惩罚 [25,26] 等技术来提高 GANs 训练的稳定性. 其中, 惩罚技术是效果较好的一类方法.…”

unclassified

Instability analysis for generative adversarial networks and its solving techniques

et al. 2020

View full text Add to dashboard Cite

Robust Image Colorization Using Self Attention Based Progressive Generative Adversarial Network

Cited by 11 publications

References 26 publications

Colorization of Logo Sketch Based on Conditional Generative Adversarial Networks

Colorization of Logo Sketch Based on Conditional Generative Adversarial Networks

Unpaired medical image colorization using generative adversarial network

Instability analysis for generative adversarial networks and its solving techniques

Contact Info

Product

Resources

About