CSCE 641 Computer Graphics: Imagebased Modeling. Jinxiang Chai. Imagebased modeling. Estimating 3D structure Estimating motion, e.g., camera motion Estimating lighting Estimating surface model. Traditional modeling and rendering. Geometry Reflectance Light source Camera model.
Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
CSCE 641 Computer Graphics: Imagebased Modeling
Jinxiang Chai
Geometry Reflectance Light source Camera model
rendering
modeling
User inputTexture map survey data
Images
For photorealism:
 Modeling is hard
 Rendering is slow
Can we model and render this?
What do we want to do for this model?
Imagebased modeling
Imagebased rendering
Imagesuser input range scans
Model
Images
Model
Panoroma
Imagebased rendering
Image based modeling
Images + Depth
Geometry+ Images
Camera + geometry
Imagesuser input range scans
Images
Geometry+ Materials
Light field
Kinematics
Dynamics
Etc.
Model
Panoroma
Imagebased rendering
Image based modeling
Images + Depth
Geometry+ Images
Camera + geometry
Imagesuser input range scans
Images
Geometry+ Materials
Light field
Kinematics
Dynamics
Etc.
Model
Panoroma
Imagebased rendering
Image based modeling
Images + Depth
Geometry+ Images
Camera + geometry
Imagesuser input range scans
Images
Geometry+ Materials
Light field
Kinematics
Dynamics
Etc.
known
camera
viewpoints
The Digital Michelangelo Project, Levoy et al.
Vicon mocap system
scene point
image plane
optical center
Perspective projection
View transformation
Viewport projection
u
sx
a
u0
v
0
sy
v0
1
0
0
1
2D projections
3D points
Camera parameters
epipolar plane
epipolar line
epipolar line
Original image pairs
Rectified image pairs
For each epipolar line
For each pixel in the left image
W = 3
W = 20


Scene
Ground truth
Windowbased matching
(best window size)
Ground truth
Ground truth
disparity map
3D rendering
[Szeliski & Kang ‘95]
input image (1 of 2)
X
z
x
x’
f
f
baseline
C
C’
all of these
points project
to the same
pair of pixels
width of
a pixel
Large Baseline
Small Baseline
1/z
width of
a pixel
width of
a pixel
pixel matching score
1/z
camera 1
camera 1
projector
projector
camera 2
Li Zhang’s oneshot stereo
The Digital Michelangelo Project, Levoy et al.
The Digital Michelangelo Project, Levoy et al.