mlsanityData to 14 Oct 2026

Delving into Crispness: Guided Label Refinement for Crisp Edge Detection

arXiv 2306.15172 ↗First posted 27 Jun 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled edges are the main cause of thick predictions. Based on this observation, we advocate that more attention should be paid on label quality than on model design to achieve crisp edge detection. To this end, we propose an effective Canny-guided refinement of human-labeled edges whose result can be used to train crisp edge detectors. Essentially, it seeks for a subset of over-detected Canny edges that best align human labels. We show that several existing edge detectors can be turned into a crisp edge detector through training on our refined edge maps. Experiments demonstrate that deep models trained with refined edges achieve significant performance boost of crispness from 17.4% to 30.6%. With the PiDiNet backbone, our method improves ODS and OIS by 12.2% and 12.6% on the Multicue dataset, respectively, without relying on non-maximal suppression. We further conduct experiments and show the superiority of our crisp edge detection for optical flow estimation and image segmentation.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

37 of 51 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  8. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  9. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  10. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  11. 2015Holistically-Nested Edge Detectioncited by 592
  12. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
25 more
  1. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  2. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  3. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 168
  4. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 163
  5. 2016Richer Convolutional Features for Edge Detectioncited by 143
  6. 2019StructureFlow: Image Inpainting via Structure-aware Appearance Flowcited by 118
  7. 2019Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detectioncited by 104
  8. 2019Foreground-aware Image Inpaintingcited by 90
  9. 2018Learning to predict crisp boundariescited by 82
  10. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  11. 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
  12. 2020Boundary-preserving Mask R-CNNcited by 74
  13. 2019Bi-Directional Cascade Network for Perceptual Edge Detectioncited by 72
  14. 2020The Edge of Depth: Explicit Constraints between Segmentation and Depthcited by 72
  15. 2014Fast Edge Detection Using Structured Forestscited by 65
  16. 2016InstanceCut: from Edges to Instances with MultiCutcited by 49
  17. 2021Enhanced Boundary Learning for Glass-like Object Segmentationcited by 48
  18. 2019EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detectioncited by 39
  19. 2015Semantic Segmentation with Boundary Neural Fieldscited by 37
  20. 2016Object Contour Detection with a Fully Convolutional Encoder-Decoder Networkcited by 34
  21. 2019Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotationscited by 32
  22. 2020Unmixing Convolutional Features for Crisp Edge Detectioncited by 32
  23. 2019Indoor Depth Completion with Boundary Consistency and Self-Attentioncited by 29
  24. 2018Simultaneous Edge Alignment and Learningcited by 22
  25. 2020FINED: Fast Inference Network for Edge Detectioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 6.

11 papers.

  1. 2025Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstructioncited by 10
  2. 2024Generative Edge Detection with Stable Diffusioncited by 5
  3. 2024Cycle Pixel Difference Network for Crisp Edge Detectioncited by 4
  4. 2026Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarioscited by 3
  5. 2025Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detectioncited by 1
  6. 2026MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervisioncited by 1
  7. 2026MEMO: Human-like Crisp Edge Detection Using Masked Edge Predictioncited by 1
  8. 2025MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNscited by 0
  9. 2026EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detectioncited by 0
  10. 2026RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmarkcited by 0
  11. 2026CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstructioncited by 0