A Benchmark for Edge-Preserving Image Smoothing

Zhu, Feida; Liang, Zhetong; Jia, Xueyuan; Zhang, Lei; Yu, Yizhou

doi:10.1109/tip.2019.2908778

Cited by 74 publications

(55 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is beneficial for high-level vision applications when sufficient humanlabeled structure/texture edges are available for training. In addition, Zhu et al [39] and Fan et al [42] propose deep learning methods to smooth texture. These methods train deep neural networks in train set firstly, and then smooth target image.…”

Section: B Structure-preserving Methodsmentioning

confidence: 99%

“…Here we evaluate the smoothing performance of our proposed method against the state of the art methods, including Huang et al [45] L0 gradient minimization [27], RGF [36], ROG [38], RTV [28], Resnet [39], VDCNN [39] and Tang et al [40]. For the Resnet and VDCNN, we use the data provided by the author to train the network.…”

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

“…Tang et al [40] increase the degree of smoothing to remove high-contrast texture while blurring some structural edge. In order to remove the textures, Huang et al [45] smooth images too much so that there is a certain degree of distortion The L0 smoothing, Resnet [39] and VDCNN [39] cannot remove high-contrast texture well. Comparing with them, RGF and RTV have a modest improvement, however, there is still a lot of texture residues.…”

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Scale and Gradient Aware Image Smoothing

Fang¹,

Yao²,

Zhang³

2019

IEEE Access

View full text Add to dashboard Cite

This paper presents a novel scale and gradient aware image smoothing method, particularly effective for removing high-contrast detailed textures while preserving boundary sharpness and fine structures. The core idea of the proposed method is based on an observation that small-scale textures can be removed only depending on a down-then-up scaling(DTUS) operation. Accordingly, we present a selective edge smoothing framework by jointly considering scale and gradient measurements. Specifically, we first compute the structural similarity(SSIM) of the DTUS image and the input image to distinguish the textures and structures from the input image. Then we use the SSIM map as weights to fuse the two images together to achieve a scale aware smoothing result. Furthermore, we use the fusion image as guidance to confine the number of non-zero gradients and perform a guided L0 gradient minimization to achieve gradient aware smoothing. Since our method makes full use of image scale and gradient, it outperforms state-of-the-art image smoothing algorithm, especially in removing high-contrast textures. Since our proposed method can remove the insignificant details while preserving sharp and undistorted structural edges, it is also adaptable to many application scenarios, such as boundary extraction, image abstraction, JPEG artifact removal, and layer decomposition-based editing.

show abstract

Section: B Structure-preserving Methodsmentioning

confidence: 99%

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Scale and Gradient Aware Image Smoothing

Fang¹,

Yao²,

Zhang³

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In 2019, Zhu et al . [23] propose a benchmark for edge‐preserving image smoothing. It constructs an image database and corresponding ground truth, but the main purpose is to combine deep learning with image smoothing.…”

Section: Introductionmentioning

confidence: 99%

Two‐stage image smoothing based on edge‐patch histogram equalisation and patch decomposition

Liu

et al. 2020

IET image process

View full text Add to dashboard Cite

Part of important structural edges in the image is smoothed due to the small gradients, while the others are preserved with greater gradients. Therefore, the authors propose a two‐stage image smoothing method based on edge‐patch histogram equalisation and patch decomposition. The authors' purpose is to increase the gradient of important structural edges while reducing the gradient of the texture region. Therefore, they divide the image into edge‐patches where the structural edges are concentrated or non‐edge‐patches where the texture details are concentrated by image segmentation. The edge‐patch needs to be equalised by the histograms for increasing the gradient of the edge pixels. All patches are decomposed to extract the smooth component for reducing the gradient of pixels. The smooth component of each patch is smoothed via L0 gradient minimisation. In order to ensure the continuity of the patch boundaries, the edge‐patch is inversely equalised. Finally, the whole image is smoothed via L0 gradient minimisation for removing residual textures and seams. Experimental results demonstrate that the proposed method is more competitive in maintaining important structural edges and removing texture details than the state‐of‐the‐art approaches. The proposed method can be applied to many areas of image processing.

show abstract

“…Feihang and Lifeng [12] proposed a gradient minimization for Chinese calligraphy works on steles to remove the noise. Zhu et al [13] described a standard for preserving edges and smoothing of images. Ma et al [14] explained image decomposition and frequency gradient approach for image smoothing.…”

Section: Introductionmentioning

confidence: 99%

Smoothing of Mammogram Using an Improved Gradient based Technique

2020

ABE

View full text Add to dashboard Cite

A Benchmark for Edge-Preserving Image Smoothing

Cited by 74 publications

References 39 publications

Scale and Gradient Aware Image Smoothing

Scale and Gradient Aware Image Smoothing

Two‐stage image smoothing based on edge‐patch histogram equalisation and patch decomposition

Smoothing of Mammogram Using an Improved Gradient based Technique

Contact Info

Product

Resources

About