10.1.1.58.6650 - MODELING AND EDITING REAL SCENES WITH...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
MODELING AND EDITING REAL SCENES WITH IMAGE-BASED TECHNIQUES by Yizhou Yu B.E.(Zhejiang University) 1992 M.S.(Zhejiang University) 1994 A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Computer Science in the GRADUATE DIVISION of the UNIVERSITY OF CALIFORNIA, BERKELEY Committee in charge: Professor Jitendra Malik, Chair Professor David A. Forsyth Professor Charles C. Benton Fall 2000
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
The dissertation of Yizhou Yu is approved: ———————————————————————- Chair Date ———————————————————————- Date ———————————————————————- Date University of California, Berkeley Fall 2000
Background image of page 2
Modeling and Editing Real Scenes with Image-Based Techniques Copyright c 2000 by Yizhou Yu
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Abstract Modeling and Editing Real Scenes with Image-based Techniques by Yizhou Yu Doctor of Philosophy in Computer Science University of California, Berkeley Professor Jitendra Malik Image-based modeling and rendering techniques greatly advanced the level of photore- alism in computer graphics. They were originally proposed to accelerate rendering with the ability to vary viewpoint only. This thesis focuses on capturing and modeling real scenes for novel visual interactions such as varying lighting condition and scene configuration in addition to viewpoint. This work can lead to applications such as virtual navigation of a real scene, interaction with the scene, novel scene composition, interior lighting design, and augmented reality. This thesis has two important parts. The first part includes the techniques to extract an object-level representation of a real scene which can be rendered with modifications to the existing spatial configuration. The key components here involve automatic algorithms to segment the geometry from range images into distinct surfaces, and register texture from radiance images with the geometry. The top-down segmentation algorithm uses a pairwise similarity measurement to recursively partition a point set into a binary tree with individual surfaces as leaves. Our image registration technique can automatically find the camera 1
Background image of page 4
poses for arbitrary position and orientation relative to the geometry. The second part includes the inverse global illumination technique which refers to re- covering reflectance models of various materials present in a real mutual illumination en- vironment. The method’s input is a geometric model of the scene and a set of calibrated photographs taken with known light source positions. The result is a lighting-independent model of the scene’s geometry and reflectance properties, which can be rendered under novel lighting conditions using traditional graphics methods. The underlying philosophy is using low-parameter BRDF models and solving optimization problems to recover the parameters. Synthetic images rendered using recovered BRDF models are comparable to real photographs.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 144

10.1.1.58.6650 - MODELING AND EDITING REAL SCENES WITH...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online