Pixel-wise Dense Detector for Image Inpainting

Loading...
Thumbnail Image
Date
2020
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial loss and reconstruction loss (e.g., `1 loss) are combined with tradeoff weights, which are also difficult to tune. In this paper, we propose a novel detection-based generative framework for image inpainting, which adopts the min-max strategy in an adversarial process. The generator follows an encoder-decoder architecture to fill the missing regions, and the detector using weakly supervised learning localizes the position of artifacts in a pixel-wise manner. Such position information makes the generator pay attention to artifacts and further enhance them. More importantly, we explicitly insert the output of the detector into the reconstruction loss with a weighting criterion, which balances the weight of the adversarial loss and reconstruction loss automatically rather than manual operation. Experiments on multiple public datasets show the superior performance of the proposed framework. The source code is available at https://github.com/Evergrow/GDN_Inpainting.
Description

        
@article{
10.1111:cgf.14160
, journal = {Computer Graphics Forum}, title = {{
Pixel-wise Dense Detector for Image Inpainting
}}, author = {
Zhang, Ruisong
and
Quan, Weize
and
Wu, Baoyuan
and
Li, Zhifeng
and
Yan, Dong-Ming
}, year = {
2020
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.14160
} }
Citation
Collections