Supervised Semantic Gradient Extraction Using Linear-Time Optimization

Abstract

This paper proposes a new supervised semantic edge and gradient extraction approach, which allows the user to roughly scribble over the desired region to extract semantically-dominant and coherent edges in it. Our approach first extracts low-level edgelets (small edge clusters) from the input image as primitives and build a graph upon them, by jointly considering both the geometric and appearance compatibility of edgelets. Given the characteristics of the graph, it cannot be effectively optimized by commonly-used energy minimization tools such as graph cuts. We thus propose an efficient linear algorithm for precise graph optimization, by taking advantage of the special structure of the graph. Objective evaluations show that the proposed method significantly outperforms previous semantic edge detection algorithms. Finally, we demonstrate the effectiveness of the system in various image editing tasks.