Awesome-Edge-Detection-Papers
A collection of edge detection papers (a.k.a. contour detection or boundary detection).
Feel free to create a PR or an issue.
Outline
1. Deep-learning based approaches
1.1 General edge detection
Short name | Paper | Source | Code/Project Link |
---|---|---|---|
BDCN | Bi-Directional Cascade Network for Perceptual Edge Detection | CVPR 2019 | [code] |
LPCB | Learning to Predict Crisp Boundaries | ECCV 2018 | |
AMH-Net | Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction | NIPS 2017 | [code] |
RCF | Richer Convolutional Features for Edge Detection | CVPR 2017 | [code-caffe] [code-pytorch] [project] |
CED | Deep Crisp Boundaries | CVPR 2017 | [code] |
COB | Convolutional Oriented Boundaries | ECCV 2016 | [code] [project] |
RDS | Learning Relaxed Deep Supervision for Better Edge Detection | CVPR 2016 | |
HFL | High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Vision | ICCV 2015 | |
HED | Holistically-Nested Edge Detection | ICCV 2015 | [code] |
DeepEdge | DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection | CVPR 2015 | |
DeepContour | DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection | CVPR 2015 |
1.2 Object contour detection
Short name | Paper | Source | Code/Project Link |
---|---|---|---|
CEDN | Object Contour Detection with a Fully Convolutional Encoder-Decoder Network | CVPR 2016 | [code-caffe] [code-TF] |
Weakly Supervised Object Boundaries | CVPR 2016 |
1.3 Semantic edge detection (Category-Aware)
Short name | Paper | Source | Code/Project Link |
---|---|---|---|
STEAL | Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations | CVPR 2019 | [project] |
DFF | Dynamic Feature Fusion for Semantic Edge Detection | 1902.09104 | |
SEAL | Simultaneous Edge Alignment and Learning | ECCV 2018 | [code] |
CASENet | CASENet: Deep Category-Aware Semantic Edge Detection | CVPR 2017 | [code] |
dataset |
Semantic Contours from Inverse Detectors | ICCV 2011 | [code] |
1.4 Occlusion boundary detection
Short name | Paper | Source | Code/Project Link |
---|---|---|---|
Occlusion Boundary Detection via Deep Exploration of Context | CVPR 2016 |
1.5 Edge detection from multi-frames
Short name | Paper | Source | Code/Project Link |
---|---|---|---|
Boundary Flow | Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion | CVPR 2018 | |
LEGO | LEGO: Learning Edge with Geometry all at Once by Watching Videos | CVPR 2018 | [code] |
Unsupervised Learning of Edges | CVPR 2016 | [code] |
2. Traditional approaches
Short name | Paper | Source | Code/Project Link |
---|---|---|---|
SemiContour | SemiContour: A Semi-supervised Learning Approach for Contour Detection | CVPR 2016 | |
OEF | Oriented Edge Forests for Boundary Detection | CVPR 2015 | [code] |
SE | Fast edge detection using structured forests | TPAMI 2015 | [code] |
Edge Boxes | Edge Boxes: Locating Object Proposals from Edges | ECCV 2014 | [code] |
PMI | Crisp Boundary Detection Using Pointwise Mutual Information | ECCV 2014 | [code] |
Sketch Tokens | Sketch tokens: A learned mid-level representation for contour and object detection | CVPR 2013 | |
SCG | Discriminatively Trained Sparse Code Gradients for Contour Detection | NIPS 2012 | |
gPb-owt-ucm | Contour Detection and Hierarchical Image Segmentation | TPAMI 2011 | [code] [project] |
Canny | A Computational Approach to Edge Detection | TPAMI 1986 |