Edge Detection

115 papers with code • 8 benchmarks • 9 datasets

Edge Detection is a fundamental image processing technique which involves computing an image gradient to quantify the magnitude and direction of edges in an image. Image gradients are used in various downstream tasks in computer vision such as line detection, feature detection, and image classification.

Source: Artistic Enhancement and Style Transfer of Image Edges using Directional Pseudo-coloring

( Image credit: Kornia )

Libraries

Use these libraries to find Edge Detection models and implementations
2 papers
9,251

Most implemented papers

Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection

xavysp/DexiNed 4 Sep 2019

This dataset has been used for training the proposed approach as well the state-of-the-art algorithms for comparisons.

On Detection of Faint Edges in Noisy Images

NatiOfir/FaintCurvedEdgeDetection 22 Jun 2017

A fundamental question for edge detection in noisy images is how faint can an edge be and still be detected.

Faster Training of Mask R-CNN by Focusing on Instance Boundaries

FlashTek/mask-rcnn-edge-agreement-loss 19 Sep 2018

We present an auxiliary task to Mask R-CNN, an instance segmentation network, which leads to faster training of the mask head.

DeepFlux for Skeletons in the Wild

YukangWang/DeepFlux CVPR 2019

In the present article, we depart from this strategy by training a CNN to predict a two-dimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms.

Bi-Directional Cascade Network for Perceptual Edge Detection

pkuCactus/BDCN CVPR 2019

Exploiting multi-scale representations is critical to improve edge detection for objects at different scales.

Object Contour and Edge Detection with RefineContourNet

AndreKelm/RefineContourNet 30 Apr 2019

A ResNet-based multi-path refinement CNN is used for object contour detection.

Edge-Direct Visual Odometry

kevinchristensen1/EdgeDirectVO 11 Jun 2019

In contrast our method builds on direct visual odometry methods naturally with minimal added computation.

A novel centroid update approach for clustering-based superpixel methods and superpixel-based edge detection

ProfHubert/Centroid 18 Oct 2019

Then according to the statistical features of noise, we propose a novel centroid update approach to enhance the robustness of clustering-based superpixel methods.

Pixel Difference Networks for Efficient Edge Detection

zhuoinoulu/pidinet ICCV 2021

A faster version of PiDiNet with less than 0. 1M parameters can still achieve comparable performance among state of the arts with 200 FPS.

SILOP: An Automated Framework for Semantic Segmentation Using Image Labels Based on Object Perimeters

erikostrowski/silop 14 Mar 2023

Our new PerimeterFit module will be applied to pre-refine the CAM predictions before using the pixel-similarity-based network.