# Pixel Difference Networks for Efficient Edge Detection

arXiv: https://arxiv.org/abs/2108.07009 · HTML: https://mlsanity.com/paper/2108.07009/

## Key facts

- Cited by 168 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 67 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Learning Rich Features from RGB-D Images for Object Detection and Segmentation](https://mlsanity.com/paper/1407.5736/) (2014)
- [NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing](https://mlsanity.com/paper/2011.02062/) (2020)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [CGNet: A Light-weight Context Guided Network for Semantic Segmentation](https://mlsanity.com/paper/1811.08201/) (2018)
- [ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network](https://mlsanity.com/paper/1811.11431/) (2018)
- [Learning to predict crisp boundaries](https://mlsanity.com/paper/1807.10097/) (2018)
- [Highly Efficient Salient Object Detection with 100K Parameters](https://mlsanity.com/paper/2003.05643/) (2020)
- [Bi-Directional Cascade Network for Perceptual Edge Detection](https://mlsanity.com/paper/1902.10903/) (2019)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection](https://mlsanity.com/paper/1412.1123/) (2014)
- [Dual-Cross Central Difference Network for Face Anti-Spoofing](https://mlsanity.com/paper/2105.01290/) (2021)
- [DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation](https://mlsanity.com/paper/1907.11357/) (2019)
- [From BoW to CNN: Two Decades of Texture Representation for Texture Classification](https://mlsanity.com/paper/1801.10324/) (2018)
- [Local Binary Convolutional Neural Networks](https://mlsanity.com/paper/1608.06049/) (2016)

## Built on by (most cited first, 30 of 168)

- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Composer: Creative and Controllable Image Synthesis with Composable Conditions](https://mlsanity.com/paper/2302.09778/) (2023)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [Sketch-Guided Text-to-Image Diffusion Models](https://mlsanity.com/paper/2211.13752/) (2022)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [CCEdit: Creative and Controllable Video Editing via Diffusion Models](https://mlsanity.com/paper/2309.16496/) (2023)
- [Low-Light Image Enhancement via Structure Modeling and Guidance](https://mlsanity.com/paper/2305.05839/) (2023)
- [TaleCrafter: Interactive Story Visualization with Multiple Characters](https://mlsanity.com/paper/2305.18247/) (2023)
- [Deep Gradient Learning for Efficient Camouflaged Object Detection](https://mlsanity.com/paper/2205.12853/) (2022)
- [Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing](https://mlsanity.com/paper/2304.02051/) (2023)
- [DREAM: Visual Decoding from Reversing Human Visual System](https://mlsanity.com/paper/2310.02265/) (2023)
- [Diffusion Model-Based Video Editing: A Survey](https://mlsanity.com/paper/2407.07111/) (2024)
- [Learning Multiple Dense Prediction Tasks from Partially Annotated Data](https://mlsanity.com/paper/2111.14893/) (2021)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort](https://mlsanity.com/paper/2311.11243/) (2023)
- [EDTER: Edge Detection with Transformer](https://mlsanity.com/paper/2203.08566/) (2022)
- [SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches](https://mlsanity.com/paper/2111.15078/) (2021)
- [Pixel-Inconsistency Modeling for Image Manipulation Localization](https://mlsanity.com/paper/2310.00234/) (2023)
- [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024)
- [GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction](https://mlsanity.com/paper/2405.19671/) (2024)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)
- [CAR: Controllable Autoregressive Modeling for Visual Generation](https://mlsanity.com/paper/2410.04671/) (2024)
- [MagicQuill: An Intelligent Interactive Image Editing System](https://mlsanity.com/paper/2411.09703/) (2024)
- [It's All About Your Sketch: Democratising Sketch Control in Diffusion Models](https://mlsanity.com/paper/2403.07234/) (2024)
- [Tiny and Efficient Model for the Edge Detection Generalization](https://mlsanity.com/paper/2308.06468/) (2023)
- [MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection](https://mlsanity.com/paper/2404.08452/) (2024)
- [The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector](https://mlsanity.com/paper/2303.11828/) (2023)
- [DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation](https://mlsanity.com/paper/2310.13119/) (2023)
- [3D-aware Conditional Image Synthesis](https://mlsanity.com/paper/2302.08509/) (2023)

## 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.