Visual coherence metric for evaluation of color image restoration

Dang, Trung Thanh; Beghdadi, Azeddine; Larabi, Mohamed–Chaker

doi:10.1109/cvcs.2013.6626268

Cited by 9 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional IQA criteria like PSNR and SSIM can only reflect part of human perception, and thus we attempt to find an alternative for them: perceptual index (PI). As visual coherence metric [52] is elaborately designed for image inpainting, PI is designed for image super-resolution. PI was firstly introduced in 2018 perceptual image restoration and manipulation (PIRM) challenge, which was a competition for perceptual image super-resolution [53].…”

Section: Benchmark Resultsmentioning

confidence: 99%

GAN-Based Image Super-Resolution with a Novel Quality Loss

Zhu

Zhang

Liu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Single image super-resolution (SISR) has been a very attractive research topic in recent years. Breakthroughs in SISR have been achieved due to deep learning and generative adversarial networks (GANs). However, the generated image still suffers from undesired artifacts. In this paper, we propose a new method named GMGAN for SISR tasks. In this method, to generate images more in line with human vision system (HVS), we design a quality loss by integrating an image quality assessment (IQA) metric named gradient magnitude similarity deviation (GMSD). To our knowledge, it is the first time to truly integrate an IQA metric into SISR. Moreover, to overcome the instability of the original GAN, we use a variant of GANs named improved training of Wasserstein GANs (WGAN-GP). Besides GMGAN, we highlight the importance of training datasets. Experiments show that GMGAN with quality loss and WGAN-GP can generate visually appealing results and set a new state of the art. In addition, large quantity of high-quality training images with rich textures can benefit the results.

show abstract

Section: Benchmark Resultsmentioning

confidence: 99%

GAN-Based Image Super-Resolution with a Novel Quality Loss

Zhu

Zhang

Liu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, currently, there is an acknowledged lack of quantitative metrics for image inpainting quality evaluation [11]. Conventional metrics are often subjective or only specifically adapted to a particular issue.…”

Section: Inpainting Resultsmentioning

confidence: 99%

A novel approach to remove foreign objects from chest X-ray images

Le¹,

Nguyen²,

Nguyen³

et al. 2020

Preprint

View full text Add to dashboard Cite

We initially proposed a deep learning approach for foreign objects inpainting in smartphone-camera captured chest radiographs utilizing the cheXphoto dataset. Foreign objects which can significantly affect the quality of a computer-aided diagnostic prediction are captured under various settings. In this paper, we used multi-method to tackle both removal and inpainting chest radiographs. Firstly, an object detection model is trained to separate the foreign objects from the given image. Subsequently, the binary mask of each object is extracted utilizing a segmentation model. Each pair of the binary mask and the extracted object are then used for inpainting purposes. Finally, the in-painted regions are now merged back to the original image, resulting in a clean and non-foreign-object-existing output. To conclude, we achieved state-of-the-art accuracy. The experimental results showed a new approach to the possible applications of this method for chest X-ray images detection.

show abstract

“…In the related literature, many research papers propose a rough classification of the inpainting methods, dividing them into three categories. The first category consists of approaches based on partial differential equation in which the missing region is filled by diffusing the image information from the known region into the missing region at the pixel level. These methods are suitable for narrow or small region but are less efficient for large district.…”

Section: Distortion Analysis Of Inpainted Thangka Imagementioning

confidence: 99%

“…The starting point of this work is to discuss an objective index that could compute the perceptual quality of the recovered Thangka image. 12 The key is that we proposed a method to decompose the reference and distorted image and to compare the intensity of fuzzy edge for structure component and similarity for texture component. By comparative analyzing the experimental results with other metrics, our approach provides a satisfied objective quality index for Thangka image.…”

mentioning

confidence: 99%

A new quality assessment for Thangka image inpainting

Liu

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary This paper presents an efficient metric for evaluation the effect of the inpainted Thangka images. In contrast to standard image quality metrics, the proposed one takes into account some constraints and characteristics related to the specific goals of inpainting techniques. The key is that we proposed a method to decompose the reference and distorted image and to compare the intensity of fuzzy edge for structure component and similarity for texture component. By comparative analyzing the experimental results with other metrics, the proposed image inpainting quality index delivers high consistency with subjective evaluation results, which will help the selecting algorithm in image restoration and could be also applied to most of inpainting image approaches.

show abstract

Visual coherence metric for evaluation of color image restoration

Cited by 9 publications

References 15 publications

GAN-Based Image Super-Resolution with a Novel Quality Loss

GAN-Based Image Super-Resolution with a Novel Quality Loss

A novel approach to remove foreign objects from chest X-ray images

A new quality assessment for Thangka image inpainting

Contact Info

Product

Resources

About