CID: Combined Image Denoising in Spatial and Frequency Domains Using Web Images

Yue, Huanjing; Sun, Xiaoyan; Yang, Jingyu; Wu, Feng

doi:10.1109/cvpr.2014.375

Cited by 36 publications

(34 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method in [31] uses web images to recover correlated images and use external patches in BM3D. Similarly, methods in [29], [30] combine internal and external patches extracted from correlated images in the BM3D framework. While these methods improve considerably restoration quality, they require that the external correlated images should be too similar to the input noisy image containing the same patterns, which is only possible in specific scenarios.…”

Section: External-based Denoisingmentioning

confidence: 99%

Low-Rankness Transfer for Realistic Denoising

Badri

Yahia

Aboutajdine

2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Current state-of-the-art denoising methods such as non-local low-rank approaches have shown to give impressive results. They are however mainly tuned to work with uniform Gaussian noise corruption and known variance, which is far from the real noise scenario. In fact, noise level estimation is already a challenging problem and denoising methods are quite sensitive to this parameter. Moreover, these methods are based on shrinkage models that are too simple to reflect reality, which results in over-smoothing of important structures such as small-scale text and textures. We propose in this paper a new approach for more realistic image restoration based on the concept of low-rankness transfer (LRT). Given a training clean/noisy image pair, our method learns a mapping between the non-local noisy singular values and the optimal values for denoising to be transfered to a new noisy input. One single image is enough for training the model and can be adapted to the noisy input by taking a correlated image. Experiments conducted on synthetic and real camera noise show that the proposed method leads to an important improvement both visually and in terms of PSNR/SSIM.

show abstract

Section: External-based Denoisingmentioning

confidence: 99%

Low-Rankness Transfer for Realistic Denoising

Badri

Yahia

Aboutajdine

2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The cloud is characterized by a large quantity of resources, storage and data [11]. Cloud based image processing has demonstrated its power in a variety of applications, such as image coding [12], deionising [13] and restoration [14]. Basically, in contrast enhancement it is difficult to choose the best parameters that will achieve visually-pleasing quality.…”

Section: Introductionmentioning

confidence: 99%

Cloud Based Image Contrast Enhancement

Wang

et al. 2015

2015 IEEE International Conference on Multimedia Big Data

View full text Add to dashboard Cite

We propose a cloud based image contrast enhancement framework, in which the context-sensitive and context-free contrast is improved via solving a multi-criteria optimization problem. Specifically, the context-sensitive contrast enhancement is based on the unsharp masking of the input and edge-preserving filtered images, while the context-free contrast enhancement is achieved by the sigmoid transfer mapping. The parameters in the optimization process are determined with the reference to the image that has a similar content and better enhancement quality in the cloud. The image complexity from the free energy based brain theory and the "surface" quality statistics is collaboratively optimized to infer the parameters. Experimental results demonstrate that the proposed technique can efficiently create visually-pleasing enhanced images with the guidance image from cloud.

show abstract

“…This method outperforms JPEG by reducing the bit-stream size by a factor of 10, while maintaining the same quality. It is worth also pointing out that similar registration techniques based on local features extracted from correlated images have also been used successfully for image superresolution [12]- [17] and image denoising [18], [19] tasks.…”

Section: B Feature-based Image Compressionmentioning

confidence: 99%