mlsanityData to 7 Oct 2026

Pixel Difference Networks for Efficient Edge Detection

arXiv 2108.07009 ↗First posted 16 Aug 2021cs.CVcited by 167

Not on the map. Why?

Cited by 29 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy consuming. In addition, it is surprising that the previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. To address these issues, we propose a simple, lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue are provided to demonstrate its effectiveness, and its high training and inference efficiency. Surprisingly, when training from scratch with only the BSDS500 and VOC datasets, PiDiNet can surpass the recorded result of human perception (0.807 vs. 0.803 in ODS F-measure) on the BSDS500 dataset with 100 FPS and less than 1M parameters. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS. Results on the NYUD and Multicue datasets show similar observations. The codes are available at https://github.com/zhuoinoulu/pidinet.

Key facts. Cited by 167 papers in the map (data through 7 Oct 2026). Builds on 41 of its 67 references that are in the map. First posted on arXiv 16 Aug 2021.

Builds on

41 of 67 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  9. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  10. 2015Holistically-Nested Edge Detectioncited by 590
  11. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  12. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
29 more
  1. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  2. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  3. 2016Richer Convolutional Features for Edge Detectioncited by 141
  4. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 124
  5. 2019Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detectioncited by 104
  6. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
  7. 2018CGNet: A Light-weight Context Guided Network for Semantic Segmentationcited by 94
  8. 2018ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Networkcited by 90
  9. 2018Learning to predict crisp boundariescited by 81
  10. 2020Highly Efficient Salient Object Detection with 100K Parameterscited by 79
  11. 2019Bi-Directional Cascade Network for Perceptual Edge Detectioncited by 71
  12. 2014Fast Edge Detection Using Structured Forestscited by 64
  13. 2017Gabor Convolutional Networkscited by 55
  14. 2014DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detectioncited by 50
  15. 2021Dual-Cross Central Difference Network for Face Anti-Spoofingcited by 47
  16. 2019DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentationcited by 45
  17. 2018From BoW to CNN: Two Decades of Texture Representation for Texture Classificationcited by 39
  18. 2016Local Binary Convolutional Neural Networkscited by 38
  19. 2015Semantic Segmentation with Boundary Neural Fieldscited by 37
  20. 2020Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognitioncited by 36
  21. 2015Pushing the Boundaries of Boundary Detection using Deep Learningcited by 35
  22. 2016Object Contour Detection with a Fully Convolutional Encoder-Decoder Networkcited by 34
  23. 2020Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeletoncited by 34
  24. 2018Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Predictioncited by 30
  25. 2014Oriented Edge Forests for Boundary Detectioncited by 25
  26. 2015High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Visioncited by 24
  27. 2020Dynamic Group Convolution for Accelerating Convolutional Neural Networkscited by 15
  28. 2020FINED: Fast Inference Network for Edge Detectioncited by 9
  29. 2020Traditional Method Inspired Deep Neural Network for Edge Detectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 41; 2024: 53; 2025: 38; 2026: 20.

167 papers.

Sort:

By area:

  1. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  2. 2023VideoComposer: Compositional Video Synthesis with Motion Controllabilitycited by 461
  3. 2023Composer: Creative and Controllable Image Synthesis with Composable Conditionscited by 303
  4. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 286
  5. 2022Sketch-Guided Text-to-Image Diffusion Modelscited by 180
  6. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 90
  7. 2023CCEdit: Creative and Controllable Video Editing via Diffusion Modelscited by 80
  8. 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 78
  9. 2023TaleCrafter: Interactive Story Visualization with Multiple Characterscited by 71
  10. 2022Deep Gradient Learning for Efficient Camouflaged Object Detectioncited by 65
  11. 2023Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editingcited by 62
  12. 2023DREAM: Visual Decoding from Reversing Human Visual Systemcited by 44
38 more
  1. 2024Diffusion Model-Based Video Editing: A Surveycited by 44
  2. 2021Learning Multiple Dense Prediction Tasks from Partially Annotated Datacited by 42
  3. 2023Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolutioncited by 39
  4. 2023AutoStory: Generating Diverse Storytelling Images with Minimal Human Effortcited by 38
  5. 2022EDTER: Edge Detection with Transformercited by 35
  6. 2023Pixel-Inconsistency Modeling for Image Manipulation Localizationcited by 33
  7. 2024DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detectioncited by 33
  8. 2021SketchEdit: Mask-Free Local Image Manipulation with Partial Sketchescited by 32
  9. 2024GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstructioncited by 31
  10. 2023Semantic Diffusion Network for Semantic Segmentationcited by 30
  11. 2024MagicQuill: An Intelligent Interactive Image Editing Systemcited by 30
  12. 2024CAR: Controllable Autoregressive Modeling for Visual Generationcited by 29
  13. 2023Tiny and Efficient Model for the Edge Detection Generalizationcited by 28
  14. 2024It's All About Your Sketch: Democratising Sketch Control in Diffusion Modelscited by 28
  15. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  16. 2023The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detectorcited by 25
  17. 2023DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagationcited by 25
  18. 20233D-aware Conditional Image Synthesiscited by 24
  19. 2024OmniControlNet: Dual-stage Integration for Conditional Image Generationcited by 24
  20. 2023NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Imagescited by 22
  21. 2024Visual Text Generation in the Wildcited by 22
  22. 2024AniDoc: Animation Creation Made Easiercited by 22
  23. 20243Doodle: Compact Abstraction of Objects with 3D Strokescited by 21
  24. 2023FreestyleRet: Retrieving Images from Style-Diversified Queriescited by 19
  25. 2024RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Lossescited by 18
  26. 2025SCALAR: Scale-wise Controllable Visual Autoregressive Learningcited by 18
  27. 2024Lightweight Pixel Difference Networks for Efficient Visual Representation Learningcited by 17
  28. 2023Reference-based Image Composition with Sketch via Structure-aware Diffusion Modelcited by 16
  29. 2024DiffDet4SAR: Diffusion-based Aircraft Target Detection Network for SAR Imagescited by 15
  30. 2025Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Trackingcited by 15
  31. 2023Learnable Differencing Center for Nighttime Depth Perceptioncited by 14
  32. 2023Practical Edge Detection via Robust Collaborative Learningcited by 12
  33. 2024Diffusion-driven GAN Inversion for Multi-Modal Face Image Generationcited by 12
  34. 20243D Neural Edge Reconstructioncited by 12
  35. 2025SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusioncited by 12
  36. 2024BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentationcited by 11
  37. 2024ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstructioncited by 11
  38. 2025Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Bettercited by 11

50 most cited of 167 All 167 (JSON)