Semantic Image Completion and Enhancement using Deep Learning

Chandak, Vaishnav; Saxena, Priyansh; Pattanaik, Manisha; Kaushal, Gaurav

doi:10.1109/icccnt45670.2019.8944750

Cited by 7 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1, illustrate our proposed image inpainting network structure, in which generative learning is supported by contextual modelling across low-frequency band and high-frequency band via the approximated DCT as described in Equations ( 1)- (3).Similar to the existing efforts [1][2][3][4][5]9], the input image is processed to drive the network by filling white pixels into the holes and their regions are indicated by a binary mask M as input pairs and the completed final image is represented as the output.…”

Section: Methodsmentioning

confidence: 99%

“…The most challenging task while reconstructing or completing the missing parts of an image is to estimate the missing region in the image. Such process often needs to take into consideration the relevant issues of image completion and de-noising simultaneously [2].Via exploitations of deep learning approaches, the quality of image inpainting has been significantly improved and the whole process is automatically managed without any human intervention [3], whilst traditional image restoration remains effective in removing noises, filling gaps with pixels and removing small defects. Irrespective of the progress achieved, image completion still imposes many challenges to researchers, as it demands "higher level of understanding the scenes".…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep image inpainting via contextual modelling in ADCT domain

Manickam

Jiang

Zhou

2022

IET Image Processing

View full text Add to dashboard Cite

Pixel-based generative image inpainting has been widely researched over recent years and certain level of success via deep learning of feature representations and hallucinations of missing pixel values from surrounding backgrounds have also been reported in the literature. However, existing approaches rely on context-based attentions and progressive inferences to capture the pixel correlations yet such pixel-based approaches often fail to adapt to the constantly varying ranges and distances among surrounding background pixels. On the other hand, the modelling cost is also increasingly expensive whenever correlations of those pixels at longer distance away are to be exploited. To resolve the problem, we implement the principle of learning and hallucinating frequency components rather than pixel values. Therefore, we can avoid the dilemma that, on one hand the wish is to exploit all correlated pixels inside the image no matter how far away they are spatially located, but on the other, the price of increasing the modelling cost incurred by those pixels far away from the missing regions has to be paid. Extensive experiments carried out verify the effectiveness of the proposed method, which outperforms the representative existing state of the arts in terms of all assessment metrics.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep image inpainting via contextual modelling in ADCT domain

Manickam

Jiang

Zhou

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Afterwards, these perturbed blocks can be reconstruct by several possible ways, e.g. low quality JPEG compression or GAN-based image completion [8] [58].…”

Section: Reconstruct Adversarial Examples To Benign Images Using Watermarking Informationmentioning

confidence: 99%

A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks

Sun

Yang

2021

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

View full text Add to dashboard Cite

Although deep learning-based models have achieved tremendous success in imagerelated tasks, they are known to be vulnerable to adversarial examples-inputs with imperceptible, but subtly crafted perturbation which fool the models to produce incorrect outputs. To distinguish adversarial examples from benign images, in this thesis, we propose a novel watermarking-based framework for protecting deep image classifiers against adversarial attacks. The proposed framework consists of a watermark encoder, a possible adversary, and a detector followed by a deep image classifier to be protected.

show abstract

“…The produced contents are either having much detail as the original one, or easily fit into the image context which appears to be visually realistic. Most of completion methods [183]are based on low-level cues to look for patches from neighbour regions of the image and create the synthesize contents that are similar to the patches. Unlike the existing models that look for patches to synthesize, the model that proposed by [184], produces contents for missing regions based on a CNN.…”

Section: Image Completionmentioning

confidence: 99%

Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies

Shamsolmoali¹,

Zareapoor²,

Granger³

et al. 2020

Preprint

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have been extremely successful in various application domains such as computer vision, medicine, and natural language processing. Moreover, transforming an object or person to a desired shape become a well-studied research in the GANs. GANs are powerful models for learning complex distributions to synthesize semantically meaningful samples. However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training. Given the current fast GANs development, in this survey, we provide a comprehensive review of adversarial models for image synthesis. We summarize the synthetic image generation methods, and discuss the categories including image-to-image translation, fusion image generation, label-to-image mapping, and text-to-image translation. We organize the literature based on their base models, developed ideas related to architectures, constraints, loss functions, evaluation metrics, and training datasets. We present milestones of adversarial models, review an extensive selection of previous works in various categories, and present insights on the development route from the model-based to data-driven methods. Further, we highlight a range of potential future research directions. One of the unique features of this review is that all software implementations of these GAN methods and datasets have been collected and made available in one place at https://github.com/pshams55/GAN-Case-Study.

show abstract

Semantic Image Completion and Enhancement using Deep Learning

Cited by 7 publications

References 20 publications

Deep image inpainting via contextual modelling in ADCT domain

Deep image inpainting via contextual modelling in ADCT domain

A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks

Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies

Contact Info

Product

Resources

About