# Deep Crisp Boundaries: From Boundaries to Higher-level Tasks

arXiv: https://arxiv.org/abs/1801.02439 · HTML: https://mlsanity.com/paper/1801.02439/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2018.

## Built on by (most cited first, 15 of 15)

- [Dense Extreme Inception Network for Edge Detection](https://mlsanity.com/paper/2112.02250/) (2021)
- [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024)
- [Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction](https://mlsanity.com/paper/2101.02843/) (2021)
- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning](https://mlsanity.com/paper/2203.09387/) (2022)
- [Cycle Pixel Difference Network for Crisp Edge Detection](https://mlsanity.com/paper/2409.04272/) (2024)
- [Zero Pixel Directional Boundary by Vector Transform](https://mlsanity.com/paper/2203.08795/) (2022)
- [Learning Good Features to Transfer Across Tasks and Domains](https://mlsanity.com/paper/2301.11310/) (2023)
- [Learning to utilize image second-order derivative information for crisp edge detection](https://mlsanity.com/paper/2406.05779/) (2024)
- [Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detection](https://mlsanity.com/paper/2504.15770/) (2025)
- [MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision](https://mlsanity.com/paper/2602.20689/) (2026)
- [Compact Twice Fusion Network for Edge Detection](https://mlsanity.com/paper/2307.04952/) (2023)
- [Holistic Geometric Feature Learning for Structured Reconstruction](https://mlsanity.com/paper/2309.09622/) (2023)
- [Msmsfnet: a multi-stream and multi-scale fusion net for edge detection](https://mlsanity.com/paper/2404.04856/) (2024)
- [UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network](https://mlsanity.com/paper/2408.04258/) (2024)

## Abstract (arXiv)

Edge detection has made significant progress with the help of deep Convolutional Networks (ConvNet). These ConvNet based edge detectors have approached human level performance on standard benchmarks. We provide a systematical study of these detectors' outputs. We show that the detection results did not accurately localize edge pixels, which can be adversarial for tasks that require crisp edge inputs. As a remedy, we propose a novel refinement architecture to address the challenging problem of learning a crisp edge detector using ConvNet. Our method leverages a top-down backward refinement pathway, and progressively increases the resolution of feature maps to generate crisp edges. Our results achieve superior performance, surpassing human accuracy when using standard criteria on BSDS500, and largely outperforming state-of-the-art methods when using more strict criteria. More importantly, we demonstrate the benefit of crisp edge maps for several important applications in computer vision, including optical flow estimation, object proposal generation and semantic segmentation.