Dollár and Zitnick (also ) propose a commonly used learning approach to edge detection based on structured random forests. The Structured Edge Detection Toolbox is available on GitHub or from Microsoft Research. Note that Dollár's Computer Vision Toolbox may be required. Examples are shown in figure 1. Further, the toolbox also includes an implementation of SLIC Superpixels .
What is your opinion on the summarized work? Or do you know related work that is of interest? Let me know your thoughts in the comments below: