Non-Photorealistic Rendering from Stereo

Abstract

A new paradigm for automatic non-photorealistic rendering is introduced in this paper. Non-photorealistic rendering (NPR) provides an alternative way to render complex scenes by emphasizing high level or salient perceptual features. Particularly, the pen-and-ink rendering style produces sketchy-like drawings that can effectively communicate shape and geometry. This is achieved by combining drawing primitives that mimic ink patterns used by artists. Existing NPR approaches can be categorized into two groups depending on the type of input they use: image based and object based. Image-based NPR techniques use 2D images to produce the renderings. Object-based techniques work directly on given 3D models and make use of the full volumetric representation. In this paper, the authors propose to enjoy the best of both worlds by developing a hybrid model that simultaneously uses information from the image and object domains. These two sources of information are provided by a calibrated stereoscopic system. Given a pair of stereo images and the calibration data, they solve the stereo problem to extract the normal and principal direction fields, which are fundamental for guiding a texture synthesis algorithm that generates the NPR renderings. In particular, normals guide tonal variations, while principal directions determine the orientation of stroke-like texture patterns. They describe a particular, fully automatic implementation of these ideas and present a number of examples.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2005
Accession Number
ADA437811

Entities

People

  • A. Bartesaghi
  • Guillermo Sapiro

Organizations

  • University of Minnesota

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Automatic
  • Boundaries
  • Calibration
  • Computer Graphics
  • Computer Vision
  • Computers
  • Data Sets
  • Eigenvalues
  • Engineering
  • Geometry
  • Illumination
  • Images
  • Low Resolution
  • Military Research
  • Orientation (Direction)
  • Shape

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Military History of the United States in the 20th Century.