Antialiasing recovery for edit propagation

Abstract

a) original image (b) result of Xu et al. (c) our result Figure 1: An example of edit propagation. (a) shows the original image and user strokes. (b) and (c) show the propagation results using the method by [Xu et al. 2009a] and our method, respectively. Alias artifacts are visible in (b) along the boundary of the building. Our method successfully eliminate these artifacts, as shown in (c). AbstractEdit propagation on images/videos has become more and more popular in recent years due to simple and intuitive interaction. It propagates sparse user edits to the whole data following the policy that nearby regions with similar appearances receive similar edits. While it gives a friendly editing mode, it often produces aliasing artifacts on edge pixels. In this paper, we present a simple algorithm to resolve this artifact for edit propagation. The key in our method is a new representation called Antialias Map, in which we represent each antialiased edge pixel by a linear interpolation of neighboring pixels around the edge, and instead of considering the original edge pixels in solving edit propagation, we consider those neighboring pixels. We demonstrate that our work is effective in preserving antialiased edges for edit propagation and could be easily integrated with existing edit propagation methods such as [Xu et al. 2009a].

Multiple Facial Image Editing Using Edge-Aware PDE Learning

“…The second category is to construct an intuitive interactive tool to reduce the manual operations of the user and a novel technique, called edit propagation , is proposed [CZL*14, XYJ13, HBZW14, SPSK13, CZZT12, MX11, FFL10, BZCC10, AP08, LLW04]. These methods propagate the sparse user edits throughout the entire image according to some pixel affinity, so that nearby similar pixels can be edited in a similar way.…”