Accurate Binary Image Selection from Inaccurate User Input

Katric Subr, Sylvain Paris, Cyril Soler, Jan Kautz

Research output: Contribution to journalArticlepeer-review

28 Citations (Scopus)


Selections 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.

Original languageEnglish
Pages (from-to)41-50
Number of pages10
JournalComputer Graphics Forum
Issue number2
Publication statusPublished - May 2013


Dive into the research topics of 'Accurate Binary Image Selection from Inaccurate User Input'. Together they form a unique fingerprint.

Cite this