Various Image Based Rendering (IBR) techniques have been proposed to reconstruct scenes from its images. Voxel-based IBR algorithms reconstruct Lambertian scenes well, but fail for specular objects due to limitations of their consistency checks. We show that the conventional consistency techniques fail due to the large variation in reflected color of the surface for different viewing positions. We present a new consistency approach that can predict this variation in color and reconstruct specular objects present in the scene. We also present an evaluation of our technique by comparing it with three other consistency methods.

Creator

• Chhabra, Vikram

Contributors

• Stevens, Mark R.

Degree

• MS

Unit

• Computer Science

Publisher

• Worcester Polytechnic Institute

Language

• English

Identifier

• etd-0427101-111305

Keyword

• graphics
• scene reconstruction
• image based rendering
• specular
• color consistency
• vision

Advisor

• Stevens, Mark R.

Defense date

• 2001-04-24

Year

• 2001

Date created

• 2001-04-27

Resource type

• Thesis

Rights statement

• In Copyright

License

• All rights reserved