Interactive example-palettes for discrete element texture synthesis

Davison, Timothy; Samavati, Faramarz; Jacob, Christian

doi:10.1016/j.cag.2018.10.016

Cited by 7 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since we randomly place elements into the output domain for fast initialization, the distribution optimization might be trapped in a local minimum when the elements are highly anisotropic and the domain is irregular. As in Figure 1a, the distribution densities in the four feet are slightly different, but this can be relieved via a teleportation scheme like [8] or a progressive initialization like [11]. In addition, our approach cannot entirely avoid interpenetrations or floating elements, but the issue is not visually obvious in our results and it is also feasible to integrate physics solvers into our framework if necessary.…”

Section: Limitations and Future Workmentioning

confidence: 95%

“…Modeling aggregate elements considering individual shapes and distributions can be achieved via data-driven methods [30,51,1,39,63,20,11] or procedural approaches [58,42,43,65,66]. By allowing merging or overlapping the elements, structures with desired appearance can be formed for practical manufacturing [82,80,6,13].…”

Section: Element Modelingmentioning

confidence: 99%

“…Interactive design systems have been presented for patterns [62,47,45,49,46,48], elements [34,33], streamlines [70,5], distributions [14,11], geometric textures [4,20,16], and dynamic effects [78], but these proposed interfaces are tailored for specific applications in 2D planes and 3D surfaces.…”

Section: Interactive Designmentioning

confidence: 99%

See 2 more Smart Citations

Autocomplete Element Fields

Hsu

Wei

You

et al. 2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

(a) graphic design (b) artistic collage (c) aggregate modeling Figure 1: Autocomplete element synthesis following partial user specifications. Our autocomplete system can be applied for different output domains such as 2D planes (a), 3D surfaces (b), and 3D volumes (c), distinct types of aggregate elements, and various applications such as design (a), collage (b), and modeling (c). The proposed system can automatically optimize the entire element distributions, orientations and scales based on the partial user strokes (a) (inset), enable users to interactively arrange the elements over the domain (b), and directly compute the volumetric output (c) from a given surface direction field (see Figure 15).

show abstract

Section: Limitations and Future Workmentioning

confidence: 95%

Section: Element Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Autocomplete Element Fields

Hsu

Wei

You

et al. 2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Overall, this work is a convincing combination of manual creation with automation for creating creative element arrangements. D avison et al [DSJ19] add to the work with a brushing technique that employs several example arrangements as palettes, which can be freely combined.…”

Section: Analysis Of the State Of The Artmentioning

confidence: 99%

A Survey of Control Mechanisms for Creative Pattern Generation

Asente

Mĕch

Beneš

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

We review recent methods in 2D creative pattern generation and their control mechanisms, focusing on procedural methods. The review is motivated by an artist's perspective and investigates interactive pattern generation as a complex design problem. While the repetitive nature of patterns is well-suited to algorithmic creation and automation, an artist needs more flexible control mechanisms for adaptable and inventive designs. We organize the state of the art around pattern design features, such as repetition, frames, curves, directionality, and single visual accents. Within those areas, we summarize and discuss the techniques' control mechanisms for enabling artist intent. The discussion includes questions of how input is given by the artist, what type of content the artist inputs, where the input affects the canvas spatially, and when input can be given in the timeline of the creation process. We categorize the available control mechanisms on an algorithmic level and categorize their input modes based on exemplars, parameterization, handling, filling, guiding, and placing interactions. To better understand the potential of the current techniques for creative design and to make such an investigation more manageable, we motivate our discussion with how navigation, transparency, variation, and stimulation enable creativity. We conclude our review by identifying possible new directions that can inspire innovation for artist-centered creation processes and algorithms. CCS Concepts• Computing methodologies → Computer graphics; • Human-centered computing → Interaction design process and methods; Interaction design theory, concepts and paradigms; Systems and tools for interaction design;

show abstract

“…TIs are usually assumed to exhibit the stationarity of the probability distribution of the desired properties and possess higher order MPS for reconstructing stochastic random samples [12,13,14,15]. Although MPS algorithms achieved in many successful applications [16,17,18,19,20,21], they suffer from some limitations inherent to the simulation algorithms. These limitations include a computational cost that can be prohibitive for high resolution three dimensional (3D) applications, the presence of visual artifacts in the model realizations, and a low variability between model realizations due to the limited pool of patterns available in a finite-size training image [22,9].…”

Section: Introductionmentioning

confidence: 99%

Fast and Scalable Earth Texture Synthesis using Spatially Assembled Generative Adversarial Neural Networks

Kim,

Yoon,

Lee

2020

Preprint

View full text Add to dashboard Cite

The earth texture with complex morphological geometry and compositions such as shale and carbonate rocks, is typically characterized with sparse field samples because of an expensive and time-consuming characterization process. Accordingly, generating arbitrary large size of the geological texture with similar topological structures at a low computation cost has become one of the key tasks for realistic geomaterial reconstruction. Recently, generative adversarial neural networks (GANs) have demonstrated a potential of synthesizing input textural images and creating equiprobable geomaterial images. However, the texture synthesis with the GANs framework is often limited by the computational cost and scalability of the output texture size. In this study, we proposed a spatially assembled GANs (SAGANs) that can generate output images of an arbitrary large size regardless of the size of training images with computational efficiency. The performance of the SAGANs was evaluated with two and three dimensional (2D and 3D) rock image samples widely used in geostatistical reconstruction of the earth texture. We demonstrate SAGANs can generate the arbitrary large size of statistical realizations with connectivity and structural properties similar to training images, and also can generate a variety of realizations even on a single training image. In addition, the computational time was significantly improved compared to standard GANs frameworks.

show abstract

Interactive example-palettes for discrete element texture synthesis

Cited by 7 publications

References 21 publications

Autocomplete Element Fields

Autocomplete Element Fields

A Survey of Control Mechanisms for Creative Pattern Generation

Fast and Scalable Earth Texture Synthesis using Spatially Assembled Generative Adversarial Neural Networks

Contact Info

Product

Resources

About