High-Precision Edge Detection via Task-Adaptive Texture Handling and Ideal-Prior Guidance

TL;DR

This paper introduces a high-precision edge detection framework that combines a novel architecture, texture differentiation, and an ideal-prior guidance strategy, achieving significant performance improvements on benchmark datasets.

Contribution

It presents SDPED, a compact edge detection model with task-adaptive architecture and a new training guidance strategy for noise-free supervision.

Findings

Up to 22.5% AP improvement on MDBD dataset

Effective texture differentiation for precise edge localization

Resolution-independent evaluation criterion

Abstract

Image edge detection (ED) requires specialized architectures, reliable supervision, and rigorous evaluation criteria to ensure accurate localization. In this work, we present a framework for high-precision ED that jointly addresses architectural design, data supervision, and evaluation consistency. We propose SDPED, a compact ED model built upon Cascaded Skipping Density Blocks (CSDB), motivated by a task-adaptive architectural transfer from image super-resolution. By re-engineering texture-oriented structures for ED, SDPED effectively differentiates textures from edges while preserving fine spatial precision. Extensive experiments on four benchmark datasets (BRIND, UDED, MDBD, and BIPED2) demonstrate consistent performance improvements, particularly in Average Precision (AP), with gains of up to 22.5% on MDBD and 11.8% on BIPED2. In addition, we introduce an ideal-prior guidance strategy that incorporates noiseless data into training by treating labels as noise-free samples, providing a practical means to mitigate the subjectivity and noise inherent in human annotations. To enable fair and resolution-independent evaluation, we further adopt a fixed-pixel criterion for assessing localization accuracy. Overall, this work offers a coherent solution for high-precision ED and provides insights applicable to precision-oriented modeling in low-level and soft-computing-based vision tasks. Codes can be found on https://github.com/Hao-B-Shu/SDPED.