Where do people draw lines?

Cole, Forrester; Golovinskiy, Aleksey; Limpaecher, Alex; Barros, Heather Stoddart; Finkelstein, Adam; Rusinkiewicz, Szymon

doi:10.1145/2063176.2063202

Cited by 33 publications

(23 citation statements)

References 17 publications

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Collecting pure ground-truth retargeting data is challenging, and quite different from collecting user data on segmentation [Martin et al 2001;Chen et al 2009], line-drawing [Cole et al 2008] or optical flow [Baker et al 2007]. Manual retargeting requires a proficient artist.…”

Section: Introductionmentioning

confidence: 99%

A comparative study of image retargeting

et al. 2010

View full text Add to dashboard Cite

CRSV MULTIOP SC SCL SM SNS WARP Figure 1: Example of retargeting the butterfly image shown in Figure 2 to half its size. In this study we evaluate 8 different image retargeting methods, asking users to compare their results and examine what qualities in retargeted images mattered to them. We also correlate the users' preferences with automatic image similarity measures. Our findings provide insights on the retargeting problem, and present a clear benchmark for future research in the field. AbstractThe numerous works on media retargeting call for a methodological approach for evaluating retargeting results. We present the first comprehensive perceptual study and analysis of image retargeting. First, we create a benchmark of images and conduct a large scale user study to compare a representative number of state-of-the-art retargeting methods. Second, we present analysis of the users' responses, where we find that humans in general agree on the evaluation of the results and show that some retargeting methods are consistently more favorable than others. Third, we examine whether computational image distance metrics can predict human retargeting perception. We show that current measures used in this context are not necessarily consistent with human rankings, and demonstrate that better results can be achieved using image features that were not previously considered for this task. We also reveal specific qualities in retargeted media that are more important for viewers. The importance of our work lies in promoting better measures to assess and guide retargeting algorithms in the future. The full benchmark we collected, including all images, retargeted results, and the collected user data, are available to the research community for further investigation at

show abstract

Section: Introductionmentioning

confidence: 99%

A comparative study of image retargeting

et al. 2010

View full text Add to dashboard Cite

show abstract

“…The field of non-photorealistic rendering for 3D scenes encompasses myriad styles that are generally oriented toward simplification and abstraction of visuals, limiting the output only to elements of high importance to human perception or central to the artist's intended "message" (Magdics et al, 2013, p. 147 of the same general line types, and these lines coincide with those in manual drawings to a significant degree (Cole et al, 2012). In addition, of course, automated algorithms can generate results on the fly, saving time and labor to an immense degree as well as reusing assets (i.e., the 3D objects in a scene).…”

Section: History Of Non-photorealistic Line Generationmentioning

confidence: 99%

“…Shape-defining line types include silhouettes, creases (ridges and valleys), and suggestive contours (Cole et al, 2012). A silhouette is an outline marking the visual discontinuity between an edge of an object and a surface or background area behind that edge.…”

Section: History Of Non-photorealistic Line Generationmentioning

confidence: 99%

Inter-color NPR Lines: A Comparison of Rendering Techniques

Herring

2016

Comput Game J

View full text Add to dashboard Cite

“…In contrast to ours, their method handles simplified interactions between two gestalts that perform as independent variables on dot lattices. In recent work by Cole et al [2008;2009], the authors study the correlation between shape conveying hand drawn lines and specific 3D shape features. Their work quantifies the strength of different line drawings at depicting shape.…”

Section: Related Workmentioning

confidence: 99%

Conjoining Gestalt rules for abstraction of architectural drawings

Nan¹,

Sharf

XieKe³

et al. 2011

ACM Trans. Graph.

View full text Add to dashboard Cite

We present a method for structural summarization and abstraction of complex spatial arrangements found in architectural drawings. The method is based on the well-known Gestalt rules, which summarize how forms, patterns, and semantics are perceived by humans from bits and pieces of geometric information. Although defining a computational model for each rule alone has been extensively studied, modeling a conjoint of Gestalt rules remains a challenge. In this work, we develop a computational framework which models Gestalt rules and more importantly, their complex interactions. We apply conjoining rules to line drawings, to detect groups of objects and repetitions that conform to Gestalt principles. We summarize and abstract such groups in ways that maintain structural semantics by displaying only a reduced number of repeated elements, or by replacing them with simpler shapes. We show an application of our method to line drawings of architectural models of various styles, and the potential of extending the technique to other computer-generated illustrations, and three-dimensional models.

show abstract

Where do people draw lines?

Cited by 33 publications

References 17 publications

A comparative study of image retargeting

A comparative study of image retargeting

Inter-color NPR Lines: A Comparison of Rendering Techniques

Conjoining Gestalt rules for abstraction of architectural drawings

Contact Info

Product

Resources

About