High relief from brush painting

Authors: Fu, Y., Yu, H., Yeh, C.K., Zhang, J. and Lee, T.Y.

Journal: IEEE Transactions on Visualization and Computer Graphics

Volume: 25

Issue: 9

Pages: 2763-2776

eISSN: 1941-0506

ISSN: 1077-2626

DOI: 10.1109/TVCG.2018.2860004

Abstract:

Relief is an art form part way between 3D sculpture and 2D painting. We present a novel approach for generating a texture-mapped high-relief model from a single brush painting. Our aim is to extract the brushstrokes from a painting and generate the individual corresponding relief proxies rather than recovering the exact depth map from the painting, which is a tricky computer vision problem, requiring assumptions that are rarely satisfied. The relief proxies of brushstrokes are then combined together to form a 2.5D high-relief model. To extract brushstrokes from 2D paintings, we apply layer decomposition and stroke segmentation by imposing boundary constraints. The segmented brushstrokes preserve the style of the input painting. By inflation and a displacement map of each brushstroke, the features of brushstrokes are preserved by the resultant high-relief model of the painting. We demonstrate that our approach is able to produce convincing high-reliefs from a variety of paintings(with humans, animals, flowers, etc.). As a secondary application, we show how our brushstroke extraction algorithm could be used for image editing. As a result, our brushstroke extraction algorithm is specifically geared towards paintings with each brushstroke drawn very purposefully, such as Chinese paintings, Rosemailing paintings, etc.

https://eprints.bournemouth.ac.uk/31215/

Source: Scopus

High Relief from Brush Painting.

Authors: Fu, Y., Yu, H., Yeh, C.-K., Zhang, J. and Lee, T.-Y.

Journal: IEEE Trans Vis Comput Graph

Volume: 25

Issue: 9

Pages: 2763-2776

eISSN: 1941-0506

DOI: 10.1109/TVCG.2018.2860004

Abstract:

Relief is an art form part way between 3D sculpture and 2D painting. We present a novel approach for generating a texture-mapped high-relief model from a single brush painting. Our aim is to extract the brushstrokes from a painting and generate the individual corresponding relief proxies rather than recovering the exact depth map from the painting, which is a tricky computer vision problem, requiring assumptions that are rarely satisfied. The relief proxies of brushstrokes are then combined together to form a 2.5D high-relief model. To extract brushstrokes from 2D paintings, we apply layer decomposition and stroke segmentation by imposing boundary constraints. The segmented brushstrokes preserve the style of the input painting. By inflation and a displacement map of each brushstroke, the features of brushstrokes are preserved by the resultant high-relief model of the painting. We demonstrate that our approach is able to produce convincing high-reliefs from a variety of paintings(with humans, animals, flowers, etc.). As a secondary application, we show how our brushstroke extraction algorithm could be used for image editing. As a result, our brushstroke extraction algorithm is specifically geared towards paintings with each brushstroke drawn very purposefully, such as Chinese paintings, Rosemailing paintings, etc.

https://eprints.bournemouth.ac.uk/31215/

Source: PubMed

High Relief from Brush Painting

Authors: Fu, Y., Yu, H., Yeh, C.-K., Zhang, J. and Lee, T.-Y.

Journal: IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS

Volume: 25

Issue: 9

Pages: 2763-2776

eISSN: 1941-0506

ISSN: 1077-2626

DOI: 10.1109/TVCG.2018.2860004

https://eprints.bournemouth.ac.uk/31215/

Source: Web of Science (Lite)

High Relief from Brush Painting

Authors: Yu, H., Zhang, J.J. and Fu, Y.

Journal: IEEE transactions on visualization and computer graphics

Publisher: IEEE

ISSN: 1077-2626

DOI: 10.1109/TVCG.2018.2860004

https://eprints.bournemouth.ac.uk/31215/

https://ieeexplore.ieee.org/document/8419282/

Source: Manual

High Relief from Brush Painting.

Authors: Fu, Y., Yu, H., Yeh, C.-K., Zhang, J. and Lee, T.-Y.

Journal: IEEE transactions on visualization and computer graphics

Volume: 25

Issue: 9

Pages: 2763-2776

eISSN: 1941-0506

ISSN: 1077-2626

DOI: 10.1109/tvcg.2018.2860004

Abstract:

Relief is an art form part way between 3D sculpture and 2D painting. We present a novel approach for generating a texture-mapped high-relief model from a single brush painting. Our aim is to extract the brushstrokes from a painting and generate the individual corresponding relief proxies rather than recovering the exact depth map from the painting, which is a tricky computer vision problem, requiring assumptions that are rarely satisfied. The relief proxies of brushstrokes are then combined together to form a 2.5D high-relief model. To extract brushstrokes from 2D paintings, we apply layer decomposition and stroke segmentation by imposing boundary constraints. The segmented brushstrokes preserve the style of the input painting. By inflation and a displacement map of each brushstroke, the features of brushstrokes are preserved by the resultant high-relief model of the painting. We demonstrate that our approach is able to produce convincing high-reliefs from a variety of paintings(with humans, animals, flowers, etc.). As a secondary application, we show how our brushstroke extraction algorithm could be used for image editing. As a result, our brushstroke extraction algorithm is specifically geared towards paintings with each brushstroke drawn very purposefully, such as Chinese paintings, Rosemailing paintings, etc.

https://eprints.bournemouth.ac.uk/31215/

Source: Europe PubMed Central

High Relief from Brush Painting

Authors: Fu, Y., Yu, H., Yeh, C.-K., Zhang, J.J. and Lee, T.-Y.

Journal: IEEE transactions on visualization and computer graphics

Volume: 25

Issue: 9

Pages: 2763-2776

ISSN: 1077-2626

Abstract:

Relief is an art form part way between 3D sculpture and 2D painting. We present a novel approach for generating a texture-mapped high-relief model from a single brush painting. Our aim is to extract the brushstrokes from a painting and generate the individual corresponding relief proxies rather than recovering the exact depth map from the painting, which is a tricky computer vision problem, requiring assumptions that are rarely satisfied. The relief proxies of brushstrokes are then combined together to form a 2.5D high-relief model. To extract brushstrokes from 2D paintings, we apply layer decomposition and stroke segmentation by imposing boundary constraints. The segmented brushstrokes preserve the style of the input painting. By inflation and a displacement map of each brushstroke, the features of brushstrokes are preserved by the resultant high-relief model of the painting. We demonstrate that our approach is able to produce convincing high-reliefs from a variety of paintings(with humans, animals, flowers, etc.). As a secondary application, we show how our brushstroke extraction algorithm could be used for image editing. As a result, our brushstroke extraction algorithm is specifically geared towards paintings with each brushstroke drawn very purposefully, such as Chinese paintings, Rosemailing paintings, etc.

https://eprints.bournemouth.ac.uk/31215/

volume:%2025%20,%20Issue:%209%20,%20Sept.%201%202019%20)

Source: BURO EPrints