New Inpainting Algorithm Based on Simplified Context Encoders and Multi-Scale Adversarial Network

Wang, Haodi; Jiao, Libin; Wu, Hao; Bie, Rongfang

doi:10.1016/j.procs.2019.01.250

Cited by 17 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, Generative Adversarial Network (GAN) becomes the most used technique in all computer vision applications. GAN-based approaches use a coarse-to-fine network and contextual attention module gives good performance and is proven to be helpful for inpainting [43][44][45][46][47]. Existing image inpainting methods based on GAN are generally a few.…”

Section: Gan-based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Image Inpainting: A Review

Elharrouss

Almaadeed

Al‐Maadeed

et al. 2019

Neural Process Lett

245

100

View full text Add to dashboard Cite

Although image inpainting, or the art of repairing the old and deteriorated images, has been around for many years, it has gained even more popularity because of the recent development in image processing techniques. With the improvement of image processing tools and the flexibility of digital image editing, automatic image inpainting has found important applications in computer vision and has also become an important and challenging topic of research in image processing. This paper is a brief review of the existing image inpainting approaches we first present a global vision on the existing methods for image inpainting. We attempt to collect most of the existing approaches and classify them into three categories, namely, sequential-based, CNN-based and GAN-based methods. In addition, for each category, a list of methods for the different types of distortion on the images is presented. Furthermore, collect a list of the available datasets and discuss these in our paper. This is a contribution for digital image inpainting researchers trying to look for the available datasets because there is a lack of datasets available for image inpainting. As the final step in this overview, we present the results of real evaluations of the three categories of image inpainting methods performed on the datasets used, for the different types of image distortion. In the end, we also present the evaluations metrics and discuss the performance of these methods in terms of these metrics. This overview can be used as a reference for image inpainting researchers, and it can also facilitate the comparison of the methods as well as the datasets used. The main contribution of this paper is the presentation of the three categories of image inpainting methods along with a list of available datasets that the researchers can use to evaluate their proposed methodology against.

show abstract

Section: Gan-based Approachesmentioning

confidence: 99%

“…In a research work named PEPSI++ [45], Shin et al propose a GAN-based method for image inpainting. Wang et al [46] use Encoder-decoder network and multi-scale GAN for image inpainting. The same combination is used in [47] for image inpainting and image-to-image transformation purposes.…”

Section: Gan-based Approachesmentioning

confidence: 99%

Image Inpainting: A Review

Elharrouss

Almaadeed

Al‐Maadeed

et al. 2019

Neural Process Lett

245

100

View full text Add to dashboard Cite

show abstract

“…Wang et al [26] uses an encoderdecoder network and a multi-scale GAN to implement image inpainting tasks. In the RBG-D image, Vitoria et al [27] proposed a modified version of the [7]. In the ocean temperature image, Dong et al [28] proposed a deep convolutional adversarial network to fill missing areas in the image.…”

Section: Image Inpaintingmentioning

confidence: 99%

“…Wang et al . [26] uses an encoder‐decoder network and a multi‐scale GAN to implement image inpainting tasks. In the RBG‐D image, Vitoria et al .…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A method of inpainting moles and acne on the high‐resolution face photos

Zhang

Liu

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

With the rapid development of mobile phones, more and more high‐resolution photos are taken. The demand for high‐resolution image inpainting is becoming increasingly urgent. In order to repair high‐resolution face images automatically and quickly, this paper proposes an improved generative adversarial networks method. Firstly, we made a high‐resolution dataset for training and testing, and abandoned the traditional 256×256 size data. Secondly, since the existing methods can only repair the mask with fixed size and shape on the image, when the global average pooling layer is used in the network, the improved network can repair the moles and acne with arbitrary sizes and shapes on the human face photos. Finally, in order to achieve optimal performance of the network, a mixed loss function is used in training. The experimental results prove that our method has not only achieved good results in qualitative results, but also achieved excellent results in quantitative results.

show abstract

Vertical‐horizontal‐context‐based high numerical precision synthesis of masked line‐scan X‐ray image

Xiong,

2024

Engineering Reports

View full text Add to dashboard Cite

Material identification based on R_value (Transparency natural logarithm ratio of low‐energy to high‐energy.) of line‐scan dual‐energy X‐ray transmission (DE‐XRT) has a good prospect for industrial application. Unfortunately, the DE‐XRT signals before attenuation within the material range cannot be directly measured, whereas their precision has essential effect on R_value. Therefore, a vertical‐horizontal‐context‐based signal synthesis method was proposed to rebuilt incomplete/masked image, which takes the filtered signals outside the material range as the reference context, and takes into account the vertical (forward/column/Y) and horizontal (scanning/row/X) anisotropy. The vertical is a time series with continuity of signal trend; the horizontal is a spatial characteristic with the fluctuation synchronization within the same row signals. The vertical curves are synthesized one by one, thus extending to the whole surface. The special rigorous synthesis evaluations of curve synthesis difference and surface synthesis difference were also proposed. Experimental results show that the tow evaluations are both only around 0.0007, and it only takes 35 ms to complete the surface synthesis of 119 × 119 pixels on the CPU with 3.4 GHz main frequency. This high numerical precision can match the similarly filtered signals after attenuation so as to improve the accuracy of R_value. And this, together with calculation real‐time, can promote the application of industrial inline material identification.

show abstract

New Inpainting Algorithm Based on Simplified Context Encoders and Multi-Scale Adversarial Network

Cited by 17 publications

References 8 publications

Image Inpainting: A Review

Image Inpainting: A Review

A method of inpainting moles and acne on the high‐resolution face photos

Vertical‐horizontal‐context‐based high numerical precision synthesis of masked line‐scan X‐ray image

Contact Info

Product

Resources

About