Computer Graphics Laboratory ETH Zurich


Smart Scribbles for Sketch Segmentation

G. Noris, D. Sykora, A. Shamir, S. Coros, B. Whited, M. Simons, A. Hornung, R. W. Sumner, M. Gross

Computer Graphics Forum, Blackwell Publishing, vol. 31, no. 8, 2012, pp. 2516-2527
[Abstract] [BibTeX] [PDF] [Video] [Video]


We present 'Smart Scribbles'-a new scribble-based interface for user-guided segmentation of digital sketchy drawings. In contrast to previous approaches based on simple selection strategies, Smart Scribbles exploits richer geometric and temporal information, resulting in a more intuitive segmentation interface. We introduce a novel energy minimization formulation in which both geometric and temporal information from digital input devices is used to define stroke-to-stroke and scribble-to-stroke relationships. Although the minimization of this energy is, in general, an NP-hard problem, we use a simple heuristic that leads to a good approximation and permits an interactive system able to produce accurate labellings even for cluttered sketchy drawings. We demonstrate the power of our technique in several practical scenarios such as sketch editing, as-rigid-as-possible deformation and registration, and on-the-fly labelling based on pre-classified guidelines.

[Download Video]

[Download Video]

@article {CGF:CGF3224,
author = {Noris, G. and Sýkora, D. and Shamir, A. and Coros, S. and Whited, B. and Simmons, M. and Hornung, A. and Gross, M. and Sumner, R.},
title = {Smart Scribbles for Sketch Segmentation},
journal = {Computer Graphics Forum},
volume = {31},
number = {8},
publisher = {Blackwell Publishing Ltd},
issn = {1467-8659},
url = {},
doi = {10.1111/j.1467-8659.2012.03224.x},
pages = {2516--2527},
keywords = {digital sketches, interactive segmentation, scribble-based user interface, energy minimization},
keywords = {I.3.4 [Computer Graphics]: Graphics Utilities—Graphics editors, I.3.6 [Computer Graphics]: Methodology and Techniques—Interaction techniques, I.5.3 [Image Processing and Computer Vision]: Clustering—Similarity measures},
year = {2012},
[Download BibTeX]


Download Paper
Download Video
Download Video