Simple data-driven modeling of brushes

Baxter, William; Govindaraju, Naga K.

doi:10.1145/1730804.1730826

Cited by 29 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Specifically, modeling deformable 3D brushes and simulating paint fluid flow through a canvas are increasingly common, and have been applied successfully for particular natural media, including watercolor [Chu and Tai 2005], oil paint [Baxter et al 2004;DiVerdi et al 2010], and pastels [Van Haevre et al 2007], with impressive results. Commercially, Microsoft's Fresh Paint application implements recent work [Chu et al 2010;Baxter and Govindaraju 2010] to create an oil paint system. However, these results are all carefully tailored to their respective natural media, and extending any of them to other types of artistic tools is difficult.…”

Section: Related Workmentioning

confidence: 99%

RealBrush

Barnes

DiVerdi

et al. 2013

ACM Trans. Graph.

View full text Add to dashboard Cite

Figure 1: A simple painting created by our system. Left to right: (a) shows oil (left) and plasticine (right) exemplars which are used to synthesize the painting in (b). The foreground flower strokes use oil exemplars, while the background strokes use plasticine and are smoothed with our smudging tool using. (c) (d) show close-ups of the smearing and smudging effects. AbstractConventional digital painting systems rely on procedural rules and physical simulation to render paint strokes. We present an interactive, data-driven painting system that uses scanned images of real natural media to synthesize both new strokes and complex stroke interactions, obviating the need for physical simulation. First, users capture images of real media, including examples of isolated strokes, pairs of overlapping strokes, and smudged strokes. Online, the user inputs a new stroke path, and our system synthesizes its 2D texture appearance with optional smearing or smudging when strokes overlap. We demonstrate high-fidelity paintings that closely resemble the captured media style, and also quantitatively evaluate our synthesis quality via user studies.

show abstract

Section: Related Workmentioning

confidence: 99%

RealBrush

Barnes

DiVerdi

et al. 2013

ACM Trans. Graph.

View full text Add to dashboard Cite

show abstract

“…In the past decades, most researchers in the field of NPR focused on modeling physical artistic medium, e.g., simulating oil painting [2] [3] [4], chinese ink and wash [5] [5] [6] crayon [7], pastel [8], viscoelastic fluid [9]. Some researchers explored new artistic media which can only be possible in digital world, e.g., 3D canvas and paints [10], taking virtual exposing as a painting medium [11], designing digital paints with virtual dynamics [12].…”

Section: Related Workmentioning

confidence: 99%

Wormhole Canvas

Lyu

Liu

Meng

et al. 2013

2013 Ninth International Conference on Computational Intelligence and Security

View full text Add to dashboard Cite

On physical canvas, color can only diffuse in the continuous 2D space. To break this constraint, this paper proposes wormhole canvas, on which the pervasive one-way wormholes can continually teleport color to distant locations. Various results show that different placements of wormholes can produce different stylized renderings. Wormhole canvas shows that NPR(Non-Photorealistic Rendering) can be the artistic media of the future, surpassing the capability of traditional artistic media.

show abstract

“…We render pastel artwork with a flat and matte appearance. For oil painting, we use a deforming brush model as in [Baxter and Govindaraju 2010]. We also simulate ridges in oil paint formed by the brush bristles and render the paint glossy.…”

Section: Paint Model Detailsmentioning

confidence: 99%

“…We perform paint simulation entirely on the GPU and brush dynamics simulation [Baxter and Govindaraju 2010] using a combination of CPU and GPU. In most cases, our system is GPU bound.…”

Section: Figure 17: a Breakdown Of Gpu Processing Cost In Our Systemmentioning

confidence: 99%

“…In this work, we focus in particular on oil and pastel, two media in which the interactions of tools and media are critical and give rise to both detail and variability. Researchers have shown that the lack of expressive variability can be addressed by moving from simple 2D bitmap -brushes‖ to more realistic models of realworld tools, such as deformable 3D paint brush models [Baxter et al 2001;Chu and Tai 2002;Adams et al 2004;Okaichi et al 2008;Baxter and Govindaraju 2010]. However, basically none of these previous techniques is able to recreate the fine details seen in real oil or pastel marks due to how the smearing and mixing of paint are implemented.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detail-preserving paint modeling for 3D brushes

Chu

Baxter

Wei

et al. 2010

Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering - NPAR 10

Self Cite

View full text Add to dashboard Cite

Figure 1: Oil paint simulated by an implementation of the system presented in [Baxter et al. 2001] (left), by our method (middle) and by the commercial package ArtRage 3 (right). Compared with [Baxter et al. 2001], our technique produces more organic color streaks and much less color blurring. Compared with the ArtRage strokes, ours appear more natural since the ArtRage method of sweeping a 1D texture to simulate strokes give less variation and control than the 3D deformable brushes offered by our system. AbstractRecent years have witnessed significant advances in 3D brush modeling and simulation in digital paint tools. Compared with traditional 2D brushes, a 3D brush can be both more intuitive and more expressive by offering an experience closer to wielding a real, physical brush. To support popular media types such as oil and pastel, most previous 3D brush models have implemented paint smearing and mixing. This is generally accomplished by a simple repeated exchange of paint between the 3D brush and 2D canvas, with the paint picked up by the brush typically mapped directly onto the brush surface. In this paper we demonstrate that both repeated exchanges and direct mapping of paint onto brush surfaces are sub-optimal choices, leading to excessive loss of color detail and computational inefficiencies. We present new techniques to solve both problems, first by using a canvas snapshot buffer to prevent repeated paint exchange, and second by mapping brush paint onto a 2D, resolution-matched pickup map that sits underneath the brush, instead of mapping onto the 3D brush itself. Together, these act to minimize resampling artifacts, helping to preserve fine streaks and color details in strokes, while at the same time yielding improved efficiency by never sampling the brush more densely than necessary. We demonstrate the effectiveness of our method in a real-time paint system implemented on the GPU that simulates pastel and oil paint. Our method is simple and effective, and achieves a level of realism for these two media not attained by any previous work.

show abstract

Simple data-driven modeling of brushes

Cited by 29 publications

References 19 publications

RealBrush

RealBrush

Wormhole Canvas

Detail-preserving paint modeling for 3D brushes

Contact Info

Product

Resources

About