(a) input image + scribbles (b) our result (c) using diffusion maps (d) using KNN mattingWe present a technique to make binary selections in images, such as to select the three penguins, using inaccurate scribbles to indicate foreground (blue) and background (red). Unlike existing approaches, our approach does not assume that the indications are 100% accurate. Since the related work, diffusion maps [FFL10] as well as KNN matting [CLT12], produce fuzzy selections, we manually thresholded their results to achieve the best possible selections.
AbstractSelections are central to image editing, e.g., they are the starting point of common operations such as copy-pasting and local edits. Creating them by hand is particularly tedious and scribble-based techniques have been introduced to assist the process. By interpolating a few strokes specified by users, these methods generate precise selections. However, most of the algorithms assume a 100% accurate input, and even small inaccuracies in the scribbles often degrade the selection quality, which imposes an additional burden on users. In this paper, we propose a selection technique tolerant to input inaccuracies. We use a dense conditional random field (CRF) to robustly infer a selection from possibly inaccurate input. Further, we show that patch-based pixel similarity functions yield more precise selection than simple point-wise metrics. However, efficiently solving a dense CRF is only possible in low-dimensional Euclidean spaces, and the metrics that we use are high-dimensional and often non-Euclidean. We address this challenge by embedding pixels in a low-dimensional Euclidean space with a metric that approximates the desired similarity function. The results show that our approach performs better than previous techniques and that two options are sufficient to cover a variety of images depending on whether the objects are textured.