AI-GAN: Signal De-Interference via Asynchronous Interactive Generative Adversarial Network

Jin, Xian-Min; Chen, Zhibo; Lin, Jianxin; Zhou, Wei; Chen, Jiale; Shan, Chaowei

doi:10.1109/icmew.2019.00046

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, GANs [1] stood out for their capability to achieve several outstanding results, relentlessly improving as [15][16][17][18][19]. Moreover, the efficiency of GAN-based image processing has been proven in many other research areas such as object classification [20] or signal restoration [21].…”

Section: Related Workmentioning

confidence: 99%

aRTIC GAN: A Recursive Text-Image-Conditioned GAN

et al. 2022

View full text Add to dashboard Cite

Generative Adversarial Networks have recently demonstrated the capability to synthesize photo-realistic real-world images. However, they still struggle to offer high controllability of the output image, even if several constraints are provided as input. In this work, we present a Recursive Text-Image-Conditioned GAN (aRTIC GAN), a novel approach for multi-conditional image generation under concurrent spatial and text constraints. It employs few line drawings and short descriptions to provide informative yet human-friendly conditioning. The proposed scenario is based on accessible constraints with high degrees of freedom: sketches are easy to draw and add strong restrictions on the generated objects, such as their orientation or main physical characteristics. Text on its side is so common and expressive that easily enforces information otherwise impossible to provide with minimal illustrations, such as objects components color, color shades, etc. Our aRTIC GAN is suitable for the sequential generation of multiple objects due to its compact design. In fact, the algorithm exploits the previously generated image in conjunction with the sketch and the text caption, resulting in a recurrent approach. We developed three network blocks to tackle the fundamental problems of catching captions’ semantic meanings and of handling the trade-off between smoothing grid-pattern artifacts and visual detail preservation. Furthermore, a compact three-task discriminator (covering global, local and textual aspects) was developed to preserve a lightweight and robust architecture. Extensive experiments proved the validity of aRTIC GAN and show that the combined use of sketch and description allows us to avoid explicit object labeling.

show abstract

Section: Related Workmentioning

confidence: 99%

aRTIC GAN: A Recursive Text-Image-Conditioned GAN

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Thereafter, many efforts are made either to introduce advancing network modules and structures, or to integrate problem-related knowledge into network design. Network modules, such as dense block [9,28,45], recursive block [9,40] and dilated convolution [5,53], and structures, such as RNN [31,40], GAN [21,29,36,60,61] and multi-stream networks [5,33,38,51,53], are validated to be effective in rain streak removal. Auxiliary information, including rain density [59], streak position [53], gradient information [49] and motion blur kernel [50], are leveraged to improve the robustness and performance of deraining networks.…”

Section: Rain Streak Removalmentioning

confidence: 99%

MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images

Shen,

Feng,

Deng

et al. 2020

Preprint

View full text Add to dashboard Cite

Rain severely hampers the visibility of scene objects when images are captured through glass in heavily rainy days. We observe three intriguing phenomenons that, 1) rain is a mixture of raindrops, rain streaks and rainy haze; 2) the depth from the camera determines the degrees of object visibility, where objects nearby and faraway are visually blocked by rain streaks and rainy haze, respectively; and 3) raindrops on the glass randomly affect the object visibility of the whole image space. We for the first time consider that, the overall visibility of objects is determined by the mixture of rain (MOR). However, existing solutions and established datasets lack full consideration of the MOR. In this work, we first formulate a new rain imaging model; by then, we enrich the popular RainCityscapes by considering raindrops, named RainCityscapes++. Furthermore, we propose a multi-branch attention generative adversarial network (termed an MBA-RainGAN) to fully remove the MOR. The experiment shows clear visual and numerical improvements of our approach over the state-of-the-arts on RainCityscapes++. The code and dataset will be available.

show abstract

VRHI: Visibility Restoration for Hazy Images Using a Haze Density Model

Chen

Liu

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

AI-GAN: Signal De-Interference via Asynchronous Interactive Generative Adversarial Network

Cited by 4 publications

References 17 publications

aRTIC GAN: A Recursive Text-Image-Conditioned GAN

aRTIC GAN: A Recursive Text-Image-Conditioned GAN

MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images

VRHI: Visibility Restoration for Hazy Images Using a Haze Density Model

Contact Info

Product

Resources

About