Accurate Binary Image Selection from Inaccurate User Input
| dc.contributor.author | Subr, Kartic | en_US |
| dc.contributor.author | Paris, Sylvain | en_US |
| dc.contributor.author | Soler, Cyril | en_US |
| dc.contributor.author | Kautz, Jan | en_US |
| dc.contributor.editor | I. Navazo, P. Poulin | en_US |
| dc.date.accessioned | 2015-02-28T15:21:12Z | |
| dc.date.available | 2015-02-28T15:21:12Z | |
| dc.date.issued | 2013 | en_US |
| dc.description.abstract | 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 percent 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. | en_US |
| dc.description.seriesinformation | Computer Graphics Forum | en_US |
| dc.identifier.issn | 1467-8659 | en_US |
| dc.identifier.uri | https://doi.org/10.1111/cgf.12024 | en_US |
| dc.publisher | The Eurographics Association and Blackwell Publishing Ltd. | en_US |
| dc.title | Accurate Binary Image Selection from Inaccurate User Input | en_US |