The Experts below are selected from a list of 261 Experts worldwide ranked by ideXlab platform
Hiroshi Ishikawa - One of the best experts on this subject based on the ideXlab platform.
-
real time data driven interactive Rough Sketch inking
International Conference on Computer Graphics and Interactive Techniques, 2018Co-Authors: Edgar Simoserra, Satoshi Iizuka, Hiroshi IshikawaAbstract:We present an interactive approach for inking, or turning a pencil Rough Sketch into a clean line drawing, based on data-driven "smart" tools that intuitively react to user input.
-
learning to simplify fully convolutional networks for Rough Sketch cleanup
International Conference on Computer Graphics and Interactive Techniques, 2016Co-Authors: Edgar Simoserra, Satoshi Iizuka, Kazuma Sasaki, Hiroshi IshikawaAbstract:In this paper, we present a novel technique to simplify Sketch drawings based on learning a series of convolution operators. In contrast to existing approaches that require vector images as input, we allow the more general and challenging input of Rough raster Sketches such as those obtained from scanning pencil Sketches. We convert the Rough Sketch into a simplified version which is then amendable for vectorization. This is all done in a fully automatic way without user intervention. Our model consists of a fully convolutional neural network which, unlike most existing convolutional neural networks, is able to process images of any dimensions and aspect ratio as input, and outputs a simplified Sketch which has the same dimensions as the input image. In order to teach our model to simplify, we present a new dataset of pairs of Rough and simplified Sketch drawings. By leveraging convolution operators in combination with efficient use of our proposed dataset, we are able to train our Sketch simplification model. Our approach naturally overcomes the limitations of existing methods, e.g., vector images as input and long computation time; and we show that meaningful simplifications can be obtained for many different test cases. Finally, we validate our results with a user study in which we greatly outperform similar approaches and establish the state of the art in Sketch simplification of raster images.
Edgar Simoserra - One of the best experts on this subject based on the ideXlab platform.
-
real time data driven interactive Rough Sketch inking
International Conference on Computer Graphics and Interactive Techniques, 2018Co-Authors: Edgar Simoserra, Satoshi Iizuka, Hiroshi IshikawaAbstract:We present an interactive approach for inking, or turning a pencil Rough Sketch into a clean line drawing, based on data-driven "smart" tools that intuitively react to user input.
-
learning to simplify fully convolutional networks for Rough Sketch cleanup
International Conference on Computer Graphics and Interactive Techniques, 2016Co-Authors: Edgar Simoserra, Satoshi Iizuka, Kazuma Sasaki, Hiroshi IshikawaAbstract:In this paper, we present a novel technique to simplify Sketch drawings based on learning a series of convolution operators. In contrast to existing approaches that require vector images as input, we allow the more general and challenging input of Rough raster Sketches such as those obtained from scanning pencil Sketches. We convert the Rough Sketch into a simplified version which is then amendable for vectorization. This is all done in a fully automatic way without user intervention. Our model consists of a fully convolutional neural network which, unlike most existing convolutional neural networks, is able to process images of any dimensions and aspect ratio as input, and outputs a simplified Sketch which has the same dimensions as the input image. In order to teach our model to simplify, we present a new dataset of pairs of Rough and simplified Sketch drawings. By leveraging convolution operators in combination with efficient use of our proposed dataset, we are able to train our Sketch simplification model. Our approach naturally overcomes the limitations of existing methods, e.g., vector images as input and long computation time; and we show that meaningful simplifications can be obtained for many different test cases. Finally, we validate our results with a user study in which we greatly outperform similar approaches and establish the state of the art in Sketch simplification of raster images.
Satoshi Iizuka - One of the best experts on this subject based on the ideXlab platform.
-
real time data driven interactive Rough Sketch inking
International Conference on Computer Graphics and Interactive Techniques, 2018Co-Authors: Edgar Simoserra, Satoshi Iizuka, Hiroshi IshikawaAbstract:We present an interactive approach for inking, or turning a pencil Rough Sketch into a clean line drawing, based on data-driven "smart" tools that intuitively react to user input.
-
learning to simplify fully convolutional networks for Rough Sketch cleanup
International Conference on Computer Graphics and Interactive Techniques, 2016Co-Authors: Edgar Simoserra, Satoshi Iizuka, Kazuma Sasaki, Hiroshi IshikawaAbstract:In this paper, we present a novel technique to simplify Sketch drawings based on learning a series of convolution operators. In contrast to existing approaches that require vector images as input, we allow the more general and challenging input of Rough raster Sketches such as those obtained from scanning pencil Sketches. We convert the Rough Sketch into a simplified version which is then amendable for vectorization. This is all done in a fully automatic way without user intervention. Our model consists of a fully convolutional neural network which, unlike most existing convolutional neural networks, is able to process images of any dimensions and aspect ratio as input, and outputs a simplified Sketch which has the same dimensions as the input image. In order to teach our model to simplify, we present a new dataset of pairs of Rough and simplified Sketch drawings. By leveraging convolution operators in combination with efficient use of our proposed dataset, we are able to train our Sketch simplification model. Our approach naturally overcomes the limitations of existing methods, e.g., vector images as input and long computation time; and we show that meaningful simplifications can be obtained for many different test cases. Finally, we validate our results with a user study in which we greatly outperform similar approaches and establish the state of the art in Sketch simplification of raster images.
Stacey Kuznetsov - One of the best experts on this subject based on the ideXlab platform.
-
a Rough Sketch of the freehand drawing process blending the line between action and artifact
Human Factors in Computing Systems, 2019Co-Authors: Piyum Fernando, Jennifer Weiler, Stacey KuznetsovAbstract:Dynamic elements of the drawing process (e.g., order of compilation, speed, length, and pressure of strokes) are considered important because they can reveal the technique, process, and emotions of the artist. To explore how sensing, visualizing, and sharing these aspects of the creative process might shape art making and art viewing experiences, we designed a research probe which unobtrusively tracks and visualizes the movement and pressure of the artist's pencil on an easel. Using our probe, we conducted studies with artists and art viewers, which reveal digital and physical representations of creative process as a means of reflecting on a multitude of factors about the finished artwork, including technique, style, and the emotions of the artists. We conclude by discussing future directions for HCI systems that sense and visualize aspects of the creative process in digitally-mediated arts, as well as the social considerations of sharing and curating intimate process information.
-
CHI - A Rough Sketch of the Freehand Drawing Process: Blending the Line between Action and Artifact
Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19, 2019Co-Authors: Piyum Fernando, Jennifer Weiler, Stacey KuznetsovAbstract:Dynamic elements of the drawing process (e.g., order of compilation, speed, length, and pressure of strokes) are considered important because they can reveal the technique, process, and emotions of the artist. To explore how sensing, visualizing, and sharing these aspects of the creative process might shape art making and art viewing experiences, we designed a research probe which unobtrusively tracks and visualizes the movement and pressure of the artist's pencil on an easel. Using our probe, we conducted studies with artists and art viewers, which reveal digital and physical representations of creative process as a means of reflecting on a multitude of factors about the finished artwork, including technique, style, and the emotions of the artists. We conclude by discussing future directions for HCI systems that sense and visualize aspects of the creative process in digitally-mediated arts, as well as the social considerations of sharing and curating intimate process information.
Piyum Fernando - One of the best experts on this subject based on the ideXlab platform.
-
a Rough Sketch of the freehand drawing process blending the line between action and artifact
Human Factors in Computing Systems, 2019Co-Authors: Piyum Fernando, Jennifer Weiler, Stacey KuznetsovAbstract:Dynamic elements of the drawing process (e.g., order of compilation, speed, length, and pressure of strokes) are considered important because they can reveal the technique, process, and emotions of the artist. To explore how sensing, visualizing, and sharing these aspects of the creative process might shape art making and art viewing experiences, we designed a research probe which unobtrusively tracks and visualizes the movement and pressure of the artist's pencil on an easel. Using our probe, we conducted studies with artists and art viewers, which reveal digital and physical representations of creative process as a means of reflecting on a multitude of factors about the finished artwork, including technique, style, and the emotions of the artists. We conclude by discussing future directions for HCI systems that sense and visualize aspects of the creative process in digitally-mediated arts, as well as the social considerations of sharing and curating intimate process information.
-
CHI - A Rough Sketch of the Freehand Drawing Process: Blending the Line between Action and Artifact
Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19, 2019Co-Authors: Piyum Fernando, Jennifer Weiler, Stacey KuznetsovAbstract:Dynamic elements of the drawing process (e.g., order of compilation, speed, length, and pressure of strokes) are considered important because they can reveal the technique, process, and emotions of the artist. To explore how sensing, visualizing, and sharing these aspects of the creative process might shape art making and art viewing experiences, we designed a research probe which unobtrusively tracks and visualizes the movement and pressure of the artist's pencil on an easel. Using our probe, we conducted studies with artists and art viewers, which reveal digital and physical representations of creative process as a means of reflecting on a multitude of factors about the finished artwork, including technique, style, and the emotions of the artists. We conclude by discussing future directions for HCI systems that sense and visualize aspects of the creative process in digitally-mediated arts, as well as the social considerations of sharing and curating intimate process information.
