Detail publikace

Rendering fur directly into images

Originální název

Rendering fur directly into images

Anglický název

Rendering fur directly into images

Jazyk

en

Originální abstrakt

We demonstrate the feasibility of rendering fur directly into existing images, without the need to either painstakingly paint over all pixels, or to supply 3D geometry and lighting. We add fur to objects depicted in images by first estimating depth and lighting information and then re-rendering the resulting 2.5D geometry with fur. A brush-based interface is provided, allowing the user to control the positioning and appearance of fur, while all the interaction takes place in a 2D pipeline. The novelty of this approach lies in the fact that a complex, high-level image edit such as the addition of fur can yield perceptually plausible results, even in the presence of imperfect depth or lighting information.

Anglický abstrakt

We demonstrate the feasibility of rendering fur directly into existing images, without the need to either painstakingly paint over all pixels, or to supply 3D geometry and lighting. We add fur to objects depicted in images by first estimating depth and lighting information and then re-rendering the resulting 2.5D geometry with fur. A brush-based interface is provided, allowing the user to control the positioning and appearance of fur, while all the interaction takes place in a 2D pipeline. The novelty of this approach lies in the fact that a complex, high-level image edit such as the addition of fur can yield perceptually plausible results, even in the presence of imperfect depth or lighting information.

BibTex


@article{BUT50943,
  author="Tania {Pouli} and Pavel {Zemčík} and Martin {Pražák} and Diego {Gutiérrez} and Erik {Reinhard}",
  title="Rendering fur directly into images",
  annote="We demonstrate the feasibility of rendering fur directly into existing images,
without the need to either painstakingly paint over all pixels, or to supply 3D
geometry and lighting. We add fur to objects depicted in images by first
estimating depth and lighting information and then re-rendering the resulting
2.5D geometry with fur. A brush-based interface is provided, allowing the user to
control the positioning and appearance of fur, while all the interaction takes
place in a 2D pipeline. The novelty of this approach lies in the fact that
a complex, high-level image edit such as the addition of fur can yield
perceptually plausible results, even in the presence of imperfect depth or
lighting information.",
  address="NEUVEDEN",
  chapter="50943",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  journal="COMPUTERS & GRAPHICS-UK",
  number="5",
  volume="34",
  year="2010",
  month="october",
  pages="612--620",
  publisher="NEUVEDEN",
  type="journal article in Web of Science"
}