Cycle Pixel Difference Network for Crisp Edge Detection

TL;DR

This paper introduces CPD-Net, a novel edge detection model that eliminates the need for large pre-trained weights and produces crisp edges by integrating cycle pixel difference convolution and multi-scale enhancement.

Contribution

The paper proposes a new cycle pixel difference convolution and a multi-scale enhancement module to improve edge detection without relying on pre-trained weights.

Findings

Achieves competitive results on multiple benchmarks.

Effectively produces crisp and clean edge contours.

Eliminates dependence on large-scale pre-trained models.

Abstract

Edge detection, as a fundamental task in computer vision, has garnered increasing attention. The advent of deep learning has significantly advanced this field. However, recent deep learning-based methods generally face two significant issues: 1) reliance on large-scale pre-trained weights, and 2) generation of thick edges. We construct a U-shape encoder-decoder model named CPD-Net that successfully addresses these two issues simultaneously. In response to issue 1), we propose a novel cycle pixel difference convolution (CPDC), which effectively integrates edge prior knowledge with modern convolution operations, consequently successfully eliminating the dependence on large-scale pre-trained weights. As for issue 2), we construct a multi-scale information enhancement module (MSEM) and a dual residual connection-based (DRC) decoder to enhance the edge location ability of the model, thereby generating crisp and clean contour maps. Comprehensive experiments conducted on four standard benchmarks demonstrate that our method achieves competitive performance on the BSDS500 dataset (ODS=0.813 and AC=0.352), NYUD-V2 (ODS=0.760 and AC=0.223), BIPED dataset (ODS=0.898 and AC=0.426), and CID (ODS=0.59). Our approach provides a novel perspective for addressing these challenges in edge detection.