# Delving into Crispness: Guided Label Refinement for Crisp Edge Detection Source: [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:28:17.841Z Authors: Yunfan Ye, Renjiao Yi, Zhirui Gao, Zhiping Cai, Kai Xu Published: 2023-06-27T03:12:58.000Z ## Abstract Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled edges are the main cause of thick predictions. Based on this observation, we advocate that more attention should be paid on label quality than on model design to achieve crisp edge detection. To this end, we propose an effective Canny-guided refinement of human-labeled edges whose result can be used to train crisp edge detectors. Essentially, it seeks for a subset of over-detected Canny edges that best align human labels. We show that several existing edge detectors can be turned into a crisp edge detector through training on our refined edge maps. Experiments demonstrate that deep models trained with refined edges achieve significant performance boost of crispness from 17.4% to 30.6%. With the PiDiNet backbone, our method improves ODS and OIS by 12.2% and 12.6% on the Multicue dataset, respectively, without relying on non-maximal suppression. We further conduct experiments and show the superiority of our crisp edge detection for optical flow estimation and image segmentation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Crisp Edge Detection on BSDS](): Crisp Edge Detection; BSDS; AC Score: 42.4. - [Crisp Edge Detection on Multi-cue](): Crisp Edge Detection; Multi-Cue; AC Score: 0.424. - [Crisp Edge Detection on BIPED](): Crisp Edge Detection; BIPED; AC Score: 0.512. - [Edge Detection on BSDS (AC, FID, LPIPS)](): Edge Detection; BSDS; AC: 42.4. ## Original sources and implementation [Original paper]() [PDF]()