Pixel Difference Networks for Efficient Edge Detection

Su, Zhuo; Liu, Wenzhe; Yu, Zitong; Hu, Dewen; Liao, Qing; Tian, Qi; Pietikäinen, Matti; Liu, Li

doi:10.1109/iccv48922.2021.00507

Cited by 209 publications

(136 citation statements)

References 57 publications

Supporting

Mentioning

123

Contrasting

Order By: Relevance

“…PiDiNet (2021): It is important to develop lightweight architectures and achieve a better trade-off between accuracy and efficiency of edge detection (Howard et al, 2017). Su et al (2021) have designed a simple, lightweight and efficient edge detection architecture called Pixel Difference Network (PiDiNet) to address these issues. PiDiNet adopts a novel pixel difference convolution (PDC) to integrate the traditional edge detection operator into the popular convolution operation in modern CNN, which enhances the performance of edge detection task.…”

Section: Edge Detection Methods Based On Multi-scale Feature Fusionmentioning

confidence: 99%

Survey of Image Edge Detection

Sun

Lei

Chen

et al. 2022

Front. Signal Process.

View full text Add to dashboard Cite

Edge detection technology aims to identify and extract the boundary information of image pixel mutation, which is a research hotspot in the field of computer vision. This technology has been widely used in image segmentation, target detection, and other high-level image processing technologies. In recent years, considering the problems of thick image edge contour, inaccurate positioning, and poor detection accuracy, researchers have proposed a variety of edge detection algorithms based on deep learning, such as multi-scale feature fusion, codec, network reconstruction, and so on. This paper dedicates to making a comprehensive analysis and special research on the edge detection algorithms. Firstly, by classifying the multi-level structure of traditional edge detection algorithms, the theory and method of each algorithm are introduced. Secondly, through focusing on the edge detection algorithm based on deep learning, the technical difficulties, advantages of methods, and backbone network selection of each algorithm are analysed. Then, through the experiments on the BSDS500 and NYUD dataset, the performance of each algorithm is further evaluated. It can be seen that the performance of the current edge detection algorithms is close to or even beyond the human visual level. At present, there are a few comprehensive review articles on image edge detection. This paper dedicates to making a comprehensive analysis of edge detection technology and aims to offer reference and guidance for the relevant personnel to follow up easily the current developments of edge detection and to make further improvements and innovations.

show abstract

Section: Edge Detection Methods Based On Multi-scale Feature Fusionmentioning

confidence: 99%

Survey of Image Edge Detection

Sun

Lei

Chen

et al. 2022

Front. Signal Process.

View full text Add to dashboard Cite

show abstract

“…To achieve effective results, BDCN [22] uses layer-specific supervision inferred from a bi-directional cascade structure to guide the training of each layer. PiDiNet [53] integrates the traditional edge detection operators into a CNN model for enhanced performance. Vision transformer.…”

Section: Related Workmentioning

confidence: 99%

“…On BSDS500. We compare our model with traditional detectors including Canny [6], Felz-Hutt [18], gPb-owtucm [2], SCG [64], Sketch Tokens [34], PMI [25], SE [15], OEF [21] and MES [50], and deep-learning-based detectors including DeepEdge [3], CSCNN [24], DeepContour [48], HFL [4], HED [65], Deep Boundary [29], CEDN [67], RDS [37], COB [40], DCD [33], AMH-Net [66], RCF [36], CED [62], LPCB [12], BDCN [22], DexiNed [52], DSCD [11] and PiDiNet [53]. The best results of all the methods are taken from their publications.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

EDTER: Edge Detection with Transformer

Pu¹,

Huang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently, vision transformer has shown excellent capability in capturing long-range dependencies. Inspired by this, we propose a novel transformer-based edge detector, Edge Detection TransformER (EDTER), to extract clear and crisp object boundaries and meaningful edges by exploiting the full image context information and detailed local cues simultaneously. EDTER works in two stages. In Stage I, a global transformer encoder is used to capture long-range global context on coarse-grained image patches. Then in Stage II, a local transformer encoder works on fine-grained patches to excavate the short-range local cues. Each transformer encoder is followed by an elaborately designed Bi-directional Multi-Level Aggregation decoder to achieve high-resolution features. Finally, the global context and local cues are combined by a Feature Fusion Module and fed into a decision head for edge prediction. Extensive experiments on BSDS500, NYUDv2, and Multicue demonstrate the superiority of EDTER in comparison with state-of-the-arts. The source code is available at https://github.com/MengyangPu/EDTER.

show abstract

“…In 2017, Liu et al [ 19 ] proposed RCF to combine features from each CNN layer efficiently. Recently, Su et al [ 20 ] considered that the edge detection algorithms based on CNN can achieve high performance because it depends on the large pretrained CNN backbone; however, it will consume a lot of memory and energy. In addition, a simple, lightweight, and effective architecture named pixel difference network (PiDiNet) for efficient edge detection was proposed.…”

Section: Introductionmentioning

confidence: 99%

Distance Field-Based Convolutional Neural Network for Edge Detection

Yang

Hou

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In this paper, we first propose an accurate edge detector using a distance field-based convolutional neural network (DF-CNN). In recent years, CNNs have been proved to be effective in image processing and computer vision. As edge detection is a fundamental problem among them, we try to improve the accuracy of edge detection based on the deep learning framework. The proposed network combines a feature extraction backbone that can fully exploit the multiscale and multilevel information of the edge with the supervised training of the distance field branch to realize the accurate end-to-end object edge detection. The distance field branch is applied to predict the Euclidean distance from nonedge points to the nearest edge point in the feature maps. And the distance information embedded in the predicted distance field map can effectively improve the accuracy of edge detection. The network is trained to minimize the weighted sum of the distance field branch loss and the cross-entropy loss. Our experimental results show that the proposed edge detector achieves better performance than previous approaches and the effectiveness of the proposed distance field branch.

show abstract

Pixel Difference Networks for Efficient Edge Detection

Cited by 209 publications

References 57 publications

Survey of Image Edge Detection

Survey of Image Edge Detection

EDTER: Edge Detection with Transformer

Distance Field-Based Convolutional Neural Network for Edge Detection

Contact Info

Product

Resources

About