Foreground-Aware Image Inpainting

Xiong, Wei; Yu, Jiahui; Lin, Zhe; Yang, Jimei; Lu, Xin; Barnes, Connelly; Luo, Jiebo

doi:10.1109/cvpr.2019.00599

Cited by 368 publications

(230 citation statements)

References 29 publications

Supporting

Mentioning

205

Contrasting

Unclassified

Order By: Relevance

“…From these categories we can find natural images, artificial images, face images, and many other categories. In this work, we attempt to collect the most used datasets for image inpainting including Paris StreetView [58], Places [59], depth image dataset [8], Foreground-aware [60], Berkeley segmentation [61], ImageNet [62] and others. We also try to cite the types of used data such as RGB images, RGB-D images and SST images.…”

Section: Image Inpainting Datasetsmentioning

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

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: Image Inpainting Datasetsmentioning

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

“…In this case, the information of either being foreground or background is an important factor in predicting the missing pixel. In [1], this problem has been addressed. To this end, in the proposed method a contour predictor has been learned which would be used as the guidance of image inpainting block.…”

Section: B Learning Approachesmentioning

confidence: 99%

“…Image inpainting is a computer vision technique that has a broad definition. It is a process that restores damaged or lost part of an image, insert an object into or remove an object from an image as the human eye could not understand it [1] [2]. According to its definition, there are many applications for it; for example, it could be used for the restoration of old images, editing or composition of an image, etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image Inpainting by Adaptive Fusion of Variable Spline Interpolations

Nabizadeh

Ghorbanzade

Karimi

et al. 2020

2020 25th International Computer Conference, Computer Society of Iran (CSICC)

View full text Add to dashboard Cite

There are many methods for image enhancement. Image inpainting is one of them which could be used in reconstruction and restoration of scratch images or editing images by adding or removing objects. According to its application, different algorithmic and learning methods are proposed. In this paper, the focus is on applications, which enhance the old and historical scratched images. For this purpose, we proposed an adaptive spline interpolation. In this method, a different number of neighbors in four directions are considered for each pixel in the lost block. In the previous methods, predicting the lost pixels that are on edges is the problem. To address this problem, we consider horizontal and vertical edge information. If the pixel is located on an edge, then we use the predicted value in that direction. In other situations, irrelevant predicted values are omitted, and the average of rest values is used as the value of the missing pixel. The method evaluates by PSNR and SSIM metrics on the Kodak dataset. The results show improvement in PSNR and SSIM compared to similar procedures. Also, the run time of the proposed method outperforms others.

show abstract

“…After that, an LSTM framework is used to chain all of them together. [37] utilize CL on the contour and image completion modules using different stages. The training starts using only the content loss, then they fine-tune it with a small weight for the adversarial loss.…”

Section: Related Workmentioning

confidence: 99%

Learning to Inpaint by Progressively Growing the Mask Regions

Hedjazi

Genç

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Image inpainting is one of the most challenging tasks in computer vision. Recently, generative-based image inpainting methods have been shown to produce visually plausible images. However, they still have difficulties to generate the correct structures and colors as the masked region grows large. This drawback is due to the training stability issue of the generative models. This work introduces a new curriculum-style training approach in the context of image inpainting. The proposed method increases the masked region size progressively in training time, during test time the user gives variable size and multiple holes at arbitrary locations. Incorporating such an approach in GANs may stabilize the training and provides better color consistencies and captures object continuities. We validate our approach on the MSCOCO and CelebA datasets. We report qualitative and quantitative comparisons of our training approach in different models.

show abstract

Foreground-Aware Image Inpainting

Cited by 368 publications

References 29 publications

Image Inpainting: A Review

Image Inpainting: A Review

Image Inpainting by Adaptive Fusion of Variable Spline Interpolations

Learning to Inpaint by Progressively Growing the Mask Regions

Contact Info

Product

Resources

About