A systematic comparison between visual cues for boundary detection

Mély, David A.; Kim, Junkyung; McGill, Mason; Guo, Yuliang; Serre, T.

doi:10.1016/j.visres.2015.11.007

Cited by 109 publications

(90 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From top to bottom: BSDS500 [2], NYUD [51], Multicue-Boundary [43], and MulticueEdge [43]. From left to right: origin image, ground truth, RCF edge map, origin image, ground truth, and RCF edge map.…”

Section: Network Discussionmentioning

confidence: 99%

“…From left to right: origin image, ground truth, RCF edge map, origin image, ground truth, and RCF edge map. Table 4: The comparison with some competitors on Multicue dataset [43].…”

Section: Network Discussionmentioning

confidence: 99%

“…ODS OIS Human-Boundary [43] .760 (.017) -Multicue-Boundary [43] .720 (.014) -HED-Boundary [60] .814 (.011) .822 (.008) RCF-Boundary .817 (.004) .825 (.005) RCF-MS-Boundary .825 (.008) .836 (.007) Human-Edge [43] .750 (.024) -Multicue-Edge [43] .830 (.002) -HED-Edge [60] . In order to investigate whether including additional nonlinearity helps, we connecting ReLU layer after 1 × 1 − 21 or 1 × 1 − 1 conv layers in each stage.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Richer Convolutional Features for Edge Detection

Liu¹,

Cheng²,

Hu³

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

581

128

View full text Add to dashboard Cite

In this paper, we propose an accurate edge detector using richer convolutional features (RCF). Since objects in natural images possess various scales and aspect ratios, learning the rich hierarchical representations is very critical for edge detection. CNNs have been proved to be effective for this task. In addition, the convolutional features in CNNs gradually become coarser with the increase of the receptive fields. According to these observations, we attempt to adopt richer convolutional features in such a challenging vision task. The proposed network fully exploits multiscale and multilevel information of objects to perform the image-to-image prediction by combining all the meaningful convolutional features in a holistic manner. Using VGG16 network, we achieve state-of-the-art performance on several available datasets. When evaluating on the well-known BSDS500 benchmark, we achieve ODS F-measure of 0.811 while retaining a fast speed (8 FPS). Besides, our fast version of RCF achieves ODS F-measure of 0.806 with 30 FPS.

show abstract

Section: Network Discussionmentioning

confidence: 99%

“…From left to right: origin image, ground truth, RCF edge map, origin image, ground truth, and RCF edge map. Table 4: The comparison with some competitors on Multicue dataset [43].…”

Section: Network Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Richer Convolutional Features for Edge Detection

Liu¹,

Cheng²,

Hu³

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

581

128

View full text Add to dashboard Cite

show abstract

“…Recently, Multicue dataset is proposed by Mély et al [43] to study psychophysics theory for boundary detection. It is composed of short binocular video sequences of 100 challenging natural scenes captured by a stereo camera.…”

Section: Multicue Datasetmentioning

confidence: 99%

Richer Convolutional Features for Edge Detection

Liu

Cheng

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

589

692

View full text Add to dashboard Cite

show abstract

“…(i) Multicue [40]: a boundary and edge detection dataset with challenging natural scenes. All 100 images are used for training.…”

Section: Datasetsmentioning

confidence: 99%

EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection

et al. 2020

View full text Add to dashboard Cite

Recently, leveraging on the development of endto-end convolutional neural networks (CNNs), deep stereo matching networks have achieved remarkable performance far exceeding traditional approaches. However, state-of-theart stereo frameworks still have difficulties at finding correct correspondences in texture-less regions, detailed structures, small objects and near boundaries, which could be alleviated by geometric clues such as edge contours and corresponding constraints. To improve the quality of disparity estimates in these challenging areas, we propose an effective multi-task learning network, EdgeStereo, composed of a disparity estimation branch and an edge detection branch, which enables end-to-end predictions of both disparity map and edge map. To effectively incorporate edge cues, we propose the edge-aware smoothness loss and edge feature embedding for inter-task interactions. It is demonstrated that based on our unified model, edge detection task and stereo matching task can promote each other. In addition, we design a compact module called residual pyramid to replace the commonly-used multi-stage cascaded structures or 3-D convolution based regularization modules in current stereo matching networks. By the time of the paper submission, EdgeStereo achieves state-of-art performance on the Fly-ingThings3D dataset, KITTI 2012 and KITTI 2015 stereo benchmarks, outperforming other published stereo matching methods by a noteworthy margin. EdgeStereo also achieves comparable generalization performance for disparity estimation because of the incorporation of edge cues.

show abstract

A systematic comparison between visual cues for boundary detection

Cited by 109 publications

References 82 publications

Richer Convolutional Features for Edge Detection

Richer Convolutional Features for Edge Detection

Richer Convolutional Features for Edge Detection

EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection

Contact Info

Product

Resources

About