Deep Crisp Boundaries
By Yupei Wang, Xin Zhao, Kaiqi Huang. 2017
134 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- EDTER: Edge Detection with Transformer (2022, methodology): “(a) Input (b) Ground truth (c) RCF [36] (d) CED [62] (e) BDCN [22] (f) EDTER (Ours)”
- RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, methodology): “As shown in Table 1, ten compared models are symbolized as HED, RCF, CED, DexiNed, BDCN, CASENet, DFF, *DeepLabV3+, *DOOBNet and *OFNet, respectively.”
- Bi-Directional Cascade Network for Perceptual Edge Detection (2019, methodology): “3% higher than current state-of-the art CED [47] on BSDS500.”
- Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection (2019, methodology): “As can Image GT CED [34] HED [36] RCF [20] BDCN [14] DexiNed be appreciated from Table 1(b), DexiNed-a reaches the best results in all evaluation metrics.”
- Pixel Difference Networks for Efficient Edge Detection (2021, methodology): “Furthermore, PiDiNet can be trained BDCNCEDRCF PiDiNetImage GT Figure 9.”
- Learning to predict crisp boundaries (2018, methodology): “The methods to be evaluated are composed of two classes: the first class is deep-learning based, which includes HED [12], RCF [13], DeepContour [11], DeepEdge [10], CED [45], HFL [47], CEDN [17], MIL+G-DSN+MS+NCuts [27] and our method; the second class contains SE [26], gPb-UCM [5] and the Canny det”
- Deep Structural Contour Detection (2020, methodology): “With the help of extra training data and multi-scale testing (the settings is also adopted by RCF/CED/LPCB and so on), our method shows obvious superiority against all the competitors.”