BézierSketch: A Generative Model for Scalable Vector Sketches

Das, Ayan; Yang, Yongxin; Hospedales, Timothy M.; Xiang, Tao; Song, Yi-Zhe

doi:10.1007/978-3-030-58574-7_38

Cited by 31 publications

(21 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18, the noses in our results are connected with the eyebrows while they are clearly separated in those from Photo-Sketching. The non-smoothness problem could be addressed by using a curve refinement technique [Das et al 2020] as post-processing. In addition, the performances on both tasks could be improved by combining the pixel-level sketch simplification or image-to-sketch model and our approach in a single end-to-end model, which may be a promising future direction.…”

Section: Limitations and Discussionmentioning

confidence: 99%

“…A number of works on learning with vector training data have been proposed in recent years, e.g., sketch reconstruction [Das et al 2020;Graves 2013;Ha and Eck 2018], and image-based drawing generation [Egiazarian et al 2020;Song et al 2018]. While, in general, it is more straightforward and easier to learn with direct vector supervision, it is not always feasible to collect vector training data.…”

Section: Related Work 21 Vector Graphics Generationmentioning

confidence: 99%

See 1 more Smart Citation

General virtual sketching framework for vector line art

Simo-Serra

Gao

et al. 2021

ACM Trans. Graph.

View full text Add to dashboard Cite

Vector line art plays an important role in graphic design, however, it is tedious to manually create. We introduce a general framework to produce line drawings from a wide variety of images, by learning a mapping from raster image space to vector image space. Our approach is based on a recurrent neural network that draws the lines one by one. A differentiable rasterization module allows for training with only supervised raster data. We use a dynamic window around a virtual pen while drawing lines, implemented with a proposed aligned cropping and differentiable pasting modules. Furthermore, we develop a stroke regularization loss that encourages the model to use fewer and longer strokes to simplify the resulting vector image. Ablation studies and comparisons with existing methods corroborate the efficiency of our approach which is able to generate visually better results in less computation time, while generalizing better to a diversity of images and applications.

show abstract

Section: Limitations and Discussionmentioning

confidence: 99%

Section: Related Work 21 Vector Graphics Generationmentioning

confidence: 99%

General virtual sketching framework for vector line art

Simo-Serra

Gao

et al. 2021

ACM Trans. Graph.

View full text Add to dashboard Cite

show abstract

“…Furthermore, even artificial sketch generators, when trained to create a sketch to convey the essence of an image with as few strokes as possible, learn to first draw lines that convey global structure and shape, prior to any details [ 34 ]. In fact, there have recently been a number of artificial neural networks trained to generate sketches that are as easily recognizable as those generated by a human [ 35 , 36 ]. We here show that drawings that take advantage of the visual system’s mechanisms for understanding scenes will be more easily interpreted [ 37 ].…”

Section: Discussionmentioning

confidence: 99%

Where to draw the line?

2021

View full text Add to dashboard Cite

We often take people’s ability to understand and produce line drawings for granted. But where should we draw lines, and why? We address psychological principles that underlie efficient representations of complex information in line drawings. First, 58 participants with varying degree of artistic experience produced multiple drawings of a small set of scenes by tracing contours on a digital tablet. Second, 37 independent observers ranked the drawings by how representative they are of the original photograph. Matching contours between drawings of the same scene revealed that the most consistently drawn contours tend to be drawn earlier. We generated half-images with the most- versus least-consistently drawn contours and asked 25 observers categorize the quickly presented scenes. Observers performed significantly better for the most compared to the least consistent half-images. The most consistently drawn contours were more likely to depict occlusion boundaries, whereas the least consistently drawn contours frequently depicted surface normals.

show abstract

“…Furthermore, even artificial sketch generators, when trained to create a sketch to convey the essence of an image with as few strokes as possible learn to first draw lines that have the most power to convey essential content [22]. In fact, there have recently been a number of artificial neural networks trained to generate sketches that are as easily recognizable as those generated by a human [23,24]. We here show that drawings that take advantage of the visual system's mechanisms for understanding scenes will be more easily interpreted [25].…”

Section: Discussionmentioning

confidence: 99%

Where to Draw The Line?

Sheng

Wilder

Walther

2021

Preprint

View full text Add to dashboard Cite

We often take people’s ability to understand and produce line drawings for granted. But where should we draw lines, and why? We address fundamental principles that underlie efficient representations of complex information in line drawings. First, 58 participants with varying degree of artistic experience produced multiple drawings of a small set of scenes by tracing contours on a digital tablet. Second, 37 independent observers ranked the drawings by how representative they are of the original photograph. Overall, artists’ drawings ranked higher than non-artists’. Matching contours between drawings of the same scene revealed that the most consistently drawn contours tend to be drawn earlier. We generated half-images with the most-versus least-consistently drawn contours by sorting contours by their consistency scores. Twenty five observers performed significantly better in a fast scene categorization task for the most compared to the least consistent half-images. The most consistent contours were longer and more likely to depict occlusion boundaries. Using psychophysics experiments and computational analysis, we confirmed quantitatively what makes certain contours in line drawings special: longer contours mark occlusion boundaries and aid rapid scene recognition. They allow artist and non-artists to convey important information starting from the first few strokes in their drawing process.

show abstract

BézierSketch: A Generative Model for Scalable Vector Sketches

Cited by 31 publications

References 25 publications

General virtual sketching framework for vector line art

General virtual sketching framework for vector line art

Where to draw the line?

Where to Draw The Line?

Contact Info

Product

Resources

About