This paper presents a novel framework for efficiently propagating the stroke-based user edits to the regions with similar colors and locations in high resolution images and videos. Our framework is based on the key ob...This paper presents a novel framework for efficiently propagating the stroke-based user edits to the regions with similar colors and locations in high resolution images and videos. Our framework is based on the key observation that the edit propagation intrinsically can also be achieved by utilizing recently proposed edge-preserving filters. Therefore, instead of adopting the traditional global optimization which may involve a time-consuming solution, our algorithm propagates edits with the aid of the edge-preserve filters. Such a propagation scheme has low computational complexity and supports multiple kinds of strokes for more flexible user interactions. Further, our method can be easily and efficiently implemented in GPU. The experimental results demonstrate the efficiency and user-friendliness of our approach.展开更多
In this paper we propose an image magnification reconstruction method. In recent years many interpolation algorithms have been proposed for image magnification, but all of them have defects to some degree, such as jag...In this paper we propose an image magnification reconstruction method. In recent years many interpolation algorithms have been proposed for image magnification, but all of them have defects to some degree, such as jaggies and blurring. To solve these problems, we propose applying post-processing which consists of edge-aware level set diffusion and bilateral filtering. After the initial interpolation, the contours of the image are identified. Next, edge-aware level set diffusion is applied to these significant contours to remove the jaggies, followed by bilateral filtering at the same locations to reduce the blurring created by the initial interpolation and level set diffusion. These processes produce sharp contours without jaggies and preserve the details of the image. Results show that the overall RMS error of our method barely increases while the contour smoothness and sharpness are substantially improved.展开更多
Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical practice.However,due to scale variation and blurry polyp boundaries,it is still a challenging task to ach...Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical practice.However,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and shapes.In this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation.Specifically,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer strategy.Besides,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale variation.Further,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual information.Finally,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation maps.Experimental results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and effectiveness.Our implementation code and segmentation maps will be publicly at https://github.com/taozh2017/EFANet.展开更多
A number of edge-aware filters can efficiently boost the appearance of an image by detail decomposition and enhancement. However, they often fail to produce photographic enhanced appearance due to some visible artifac...A number of edge-aware filters can efficiently boost the appearance of an image by detail decomposition and enhancement. However, they often fail to produce photographic enhanced appearance due to some visible artifacts, especially noise, halos and unnatural contrast. The essential reason is that the guidance and the constraint of high-quality appearance are not sufficient enough in the process of enhancement. Thus our idea is to train a detail dictionary from a lot of high-quality patches in order to constrain and control the entire appearance enhancement. In this paper, we propose a novel learning-based enhancement method for photographic appearance, which includes two main stages： dictionary training and sparse reconstruction. In the training stage, we construct a training set of detail patches extracted from some high-quality photos, and then train an overcomplete detail dictionary by iteratively minimizing an？1-norm energy function. In the reconstruction stage, we employ the trained dictionary to reconstruct the boosted detail layer, and further formalize a gradient-guided optimization function to improve the local coherence between patches. Moreover, we propose two evaluation metrics to measure the performance of appearance enhancement. The final experimental results have demonstrated the effectiveness of our learning-based enhancement method.展开更多
The traditional space-invariant isotropic kernel utilized by a bilateral filter(BF)frequently leads to blurry edges and gradient reversal artifacts due to tlie existence of a large amount of outliers in the local aver...The traditional space-invariant isotropic kernel utilized by a bilateral filter(BF)frequently leads to blurry edges and gradient reversal artifacts due to tlie existence of a large amount of outliers in the local averaging window.However,the efficient and accurate cstiinatioii of space-variant k(4rnels which adapt to image structures,and the fast realization of the corresponding space-variant bilateral filtering are challenging problems.To address these problems,we present a space-variant BF(SVBF).and its linear time and error-bounded acceleration method.First,we accurately estimate spacevariant,anisotropic kernels that vary with image structures in linear time through structure tensor and mininnini spanning tree.Second,we perform SVBF in linear time using two error-bounded approximation methods,namely,low-rank tensor approximation via higher-order singular value decomposition and exponential sum approximation.Tlierefore.the proposed SVBF can efficiently achieve good edge-preserving results.We validate the advantages of the proposed filter in applications including:image denoising,image enhancement,and image focus editing.Experimental results(leinonstrate that our fast and error-bounded SVBF is superior to state-of-the-art methods.展开更多
基金supported by the National Natural Science Foundation of China under Grant No.61003132the National High Technology Research and Development 863 Program of China under Grant No. 2010AA012400
文摘This paper presents a novel framework for efficiently propagating the stroke-based user edits to the regions with similar colors and locations in high resolution images and videos. Our framework is based on the key observation that the edit propagation intrinsically can also be achieved by utilizing recently proposed edge-preserving filters. Therefore, instead of adopting the traditional global optimization which may involve a time-consuming solution, our algorithm propagates edits with the aid of the edge-preserve filters. Such a propagation scheme has low computational complexity and supports multiple kinds of strokes for more flexible user interactions. Further, our method can be easily and efficiently implemented in GPU. The experimental results demonstrate the efficiency and user-friendliness of our approach.
基金supported by the National Natural Science Foundation of China under Grant Nos.60703003 and 60641002
文摘In this paper we propose an image magnification reconstruction method. In recent years many interpolation algorithms have been proposed for image magnification, but all of them have defects to some degree, such as jaggies and blurring. To solve these problems, we propose applying post-processing which consists of edge-aware level set diffusion and bilateral filtering. After the initial interpolation, the contours of the image are identified. Next, edge-aware level set diffusion is applied to these significant contours to remove the jaggies, followed by bilateral filtering at the same locations to reduce the blurring created by the initial interpolation and level set diffusion. These processes produce sharp contours without jaggies and preserve the details of the image. Results show that the overall RMS error of our method barely increases while the contour smoothness and sharpness are substantially improved.
基金supported in part by National Natural Science Foundation of China(Nos.62172228,62201263,62106043 and 62201265).
文摘Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical practice.However,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and shapes.In this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation.Specifically,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer strategy.Besides,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale variation.Further,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual information.Finally,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation maps.Experimental results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and effectiveness.Our implementation code and segmentation maps will be publicly at https://github.com/taozh2017/EFANet.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos. 61303093, 61402278, and 61472245, the Innovation Program of the Science and Technology Commission of Shanghai Municipality of China under Grant No. 16511101300, the Natural Science Foundation of Shanghai under Grant No. 14ZR1415800, and the Gaofeng Film Discipline Grant of Shanghai Municipal Education Commission.
文摘A number of edge-aware filters can efficiently boost the appearance of an image by detail decomposition and enhancement. However, they often fail to produce photographic enhanced appearance due to some visible artifacts, especially noise, halos and unnatural contrast. The essential reason is that the guidance and the constraint of high-quality appearance are not sufficient enough in the process of enhancement. Thus our idea is to train a detail dictionary from a lot of high-quality patches in order to constrain and control the entire appearance enhancement. In this paper, we propose a novel learning-based enhancement method for photographic appearance, which includes two main stages： dictionary training and sparse reconstruction. In the training stage, we construct a training set of detail patches extracted from some high-quality photos, and then train an overcomplete detail dictionary by iteratively minimizing an？1-norm energy function. In the reconstruction stage, we employ the trained dictionary to reconstruct the boosted detail layer, and further formalize a gradient-guided optimization function to improve the local coherence between patches. Moreover, we propose two evaluation metrics to measure the performance of appearance enhancement. The final experimental results have demonstrated the effectiveness of our learning-based enhancement method.
基金the National Natural Science Foundation of China under Grant Nos.61620106003.61701235,61772523,61471338 and 61571046the Beijing Natural Science Foundation of China under Grant,No.LI82059+1 种基金the Fundamental Research Funds for the Central Universities of China under Grant No.30917011323the Open Projects Program of National Laboratory of Pattern Recognition of China under Grant No.201900020.
文摘The traditional space-invariant isotropic kernel utilized by a bilateral filter(BF)frequently leads to blurry edges and gradient reversal artifacts due to tlie existence of a large amount of outliers in the local averaging window.However,the efficient and accurate cstiinatioii of space-variant k(4rnels which adapt to image structures,and the fast realization of the corresponding space-variant bilateral filtering are challenging problems.To address these problems,we present a space-variant BF(SVBF).and its linear time and error-bounded acceleration method.First,we accurately estimate spacevariant,anisotropic kernels that vary with image structures in linear time through structure tensor and mininnini spanning tree.Second,we perform SVBF in linear time using two error-bounded approximation methods,namely,low-rank tensor approximation via higher-order singular value decomposition and exponential sum approximation.Tlierefore.the proposed SVBF can efficiently achieve good edge-preserving results.We validate the advantages of the proposed filter in applications including:image denoising,image enhancement,and image focus editing.Experimental results(leinonstrate that our fast and error-bounded SVBF is superior to state-of-the-art methods.
