Feature-Based Image Metamorphosis Thaddeus Beier Shawn Neely SIGGRAPH 1992.

Feature-Based Image Metamorphosis

Thaddeus Beier Shawn Neely

SIGGRAPH 1992

Image Morphing History

Morphing is turning one image into another through a seamless transition

Michael Jackson’s “Black or White”Cross-fading

morphing

cross-fadingImage morphing

image #1 image #2

warp warp

Image morphing

Morphing = warping + cross-dissolving

shape

(geometric)

color

(photometric)

Warp = feature specification + warp generation

Warp specification

• How can we specify the warp?3. Specify corresponding spline control points

• interpolate to a complete warping function

But we want to specify only a few points, not a grid

Warp specification

• How can we specify the warp?1. Specify corresponding points

• interpolate to a complete warping function• How do we do it?

Warp specification

• How can we specify the warp?2. Specify corresponding vectors

• interpolate to a complete warping function• The Beier & Neely Algorithm

Two basic styles

• Forward warping

• Reverse mapping

Single line-pair PQ to P’Q’

Single Line-pair Examples

Multiple Lines

Length = length of the line segment, dist = distance to line segmenta, p, b – constants. What do they do?

Resulting warp (complex!)

Full Algorithm

Animation• Here's how you create an animated morph:• GenerateAnimation(Image0, L0[...],Image1, L1[...])• begin• foreach intermediate frame time t do• for i=1 to number of line-pairs do• L[i] = line t-th of the way from L0[i] to L1[i].• end• Warp0 = WarpImage( Image0, L0[...], L[...])• Warp1 = WarpImage( Image1, L1[...], L[...])• foreach pixel p in FinalImage do• FinalImage(p) = (1-t) Warp0(p) + t Warp1(p)• end• end• end

Interpolating Lines

• Method 1: interpolating endpoints

• Method 2: interpolating midpoints, length and orientation.

Results

Dynamic Scene

Algorithm summary

Morphing & matting• Extract foreground first to avoid artifacts in

the background

Uniform morphing

Non-uniform morphing

Procedural Transformation

Multi-source morphing

Manipulating Facial Appearance through Shape

and ColorDuncan A. Rowland and David I. P

errett

St Andrews University

IEEE CG&A, September 1995

The Morphable Face Model

• shape vector S = (x1, y1, x2, …, yn)T

• appearance (texture) vector T = (R1, G1, B1, R2, …, Gn, Bn)T

Shape S

Appearance T

The Morphable face model

• Assuming that we have m such vector pairs in full correspondence, we can form new shapes Smodel and new appearances Tmodel as:

• If number of basis faces m is large enough to span the face subspace then:

• Any new face can be represented as a pair of vectors

m

iiimodel a

1

SS

m

iiimodel b

1

TT

Face averaging by morphing

average faces

http://www.beautycheck.de

Subpopulation means

• Examples:– Happy faces– Young faces– Asian faces– Etc.– Sunny days– Rainy days– Etc.– Etc.

Average male

Average female

The average face

Women In Arts

http://www.youtube.com/watch?v=nUDIoN-_Hxs

References• Thaddeus Beier, Shawn Neely, Feature-Based Image Metamorphosis,

SIGGRAPH 1992, pp35-42. • Detlef Ruprecht, Heinrich Muller, Image Warping with Scattered Data

Interpolation, IEEE Computer Graphics and Applications, March 1995, pp37-43.

• Seung-Yong Lee, Kyung-Yong Chwa, Sung Yong Shin, Image Metamorphosis Using Snakes and Free-Form Deformations, SIGGRAPH 1995.

• Seungyong Lee, Wolberg, G., Sung Yong Shin, Polymorph: morphing among multiple images, IEEE Computer Graphics and Applications, Vol. 18, No. 1, 1998, pp58-71.

• Peinsheng Gao, Thomas Sederberg, A work minimization approach to image morphing, The Visual Computer, 1998, pp390-400.

• George Wolberg, Image morphing: a survey, The Visual Computer, 1998, pp360-372.

Overview of Morphing Methods

– Mesh Warping– Field Morphing– Radial Basis Function– Energy minimization– Multilevel Free-Form Deformation– Work minimization

Image Morphing: A Survey George Wolberg 1998