SOTAVerified

Edge Detection

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 )

Papers

Showing 1–25 of 490 papers

TitleStatusHype
OmniGen: Unified Image GenerationCode7
Lightweight Pixel Difference Networks for Efficient Visual Representation LearningCode4
DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge DetectionCode3
Rethinking Boundary Detection in Deep Learning-Based Medical Image SegmentationCode2
Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing ImageryCode2
Tiny and Efficient Model for the Edge Detection GeneralizationCode2
Low-Light Image Enhancement via Structure Modeling and GuidanceCode2
Visual Prompting via Image InpaintingCode2
EDTER: Edge Detection with TransformerCode2
A Doubly Decoupled Network for edge detectionCode1
STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point CloudsCode1
EDMB: Edge Detector with MambaCode1
SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge DetectionCode1
A new baseline for edge detection: Make Encoder-Decoder great againCode1
Mismatched: Evaluating the Limits of Image Matching Approaches and BenchmarksCode1
EdgeNAT: Transformer for Efficient Edge DetectionCode1
GUI Element Detection Using SOTA YOLO Deep Learning ModelsCode1
AnomalyLLM: Few-shot Anomaly Edge Detection for Dynamic Graphs using Large Language ModelsCode1
Leveraging edge detection and neural networks for better UAV localizationCode1
RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based LossesCode1
SuperEdge: Towards a Generalization Model for Self-Supervised Edge DetectionCode1
Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect SegmentationCode1
Meta ControlNet: Enhancing Task Adaptation via Meta LearningCode1
MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp SegmentationCode1
Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model EstimationCode1
Show:102550
← PrevPage 1 of 20Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DDNODS0.92—Unverified
2DexiNedODS0.9—Unverified
3BDCNODS0.89—Unverified
4LDCODS0.89—Unverified
5CATSODS0.89—Unverified
6RCFODS0.85—Unverified
#ModelMetricClaimedVerifiedStatus
1DexiNed-aODS0.89—Unverified
2DexiNed-fODS0.89—Unverified
3CATSODS0.89—Unverified
4BDCNODS0.89—Unverified
5LDCODS0.88—Unverified
6RCFODS0.88—Unverified
#ModelMetricClaimedVerifiedStatus
1DDNODS0.83—Unverified
2TEEDODS0.83—Unverified
3LDCODS0.82—Unverified
4DexiNedODS0.82—Unverified
5PiDiNetODS0.81—Unverified
#ModelMetricClaimedVerifiedStatus
1LDCODS0.79—Unverified
2BDCNODS0.79—Unverified
3PiDiNetODS0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1SEDODS0.65—Unverified
2DexiNed (WACV'2020)ODS0.65—Unverified
#ModelMetricClaimedVerifiedStatus
1RPCNetAP86.15—Unverified
2CASENetAP70.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CASENetMaximum F-measure71.4—Unverified
2WSOBMaximum F-measure52—Unverified
#ModelMetricClaimedVerifiedStatus
1RCNF10.82—Unverified