An Image Morphing Technique Based on Optimal Mass Preserving Mapping
- 15 May 2007
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 16 (6) , 1481-1495
Abstract
Image morphing, or image interpolation in the time domain, deals with the metamorphosis of one image into another. In this paper, a new class of image morphing algorithms is proposed based on the theory of optimal mass transport. The L2 mass moving energy functional is modified by adding an intensity penalizing term, in order to reduce the undesired double exposure effect. It is an intensity-based approach and, thus, is parameter free. The optimal warping function is computed using an iterative gradient descent approach. This proposed morphing method is also extended to doubly connected domains using a harmonic parameterization technique, along with finite-element methodsKeywords
This publication has 30 references indexed in Scilit:
- Numerical methods for volume preserving image registrationInverse Problems, 2004
- Target-driven smoke animationACM Transactions on Graphics, 2004
- An eulerian pde approach for computing tissue thicknessIEEE Transactions on Medical Imaging, 2003
- Keyframe control of smoke simulationsACM Transactions on Graphics, 2003
- Minimizing Flows for the Monge--Kantorovich ProblemSIAM Journal on Mathematical Analysis, 2003
- Nondistorting flattening maps and the 3-D visualization of colon CT imagesIEEE Transactions on Medical Imaging, 2000
- Deformable 2-D template matching using orthogonal curvesIEEE Transactions on Medical Imaging, 1997
- Optical flow computation using extended constraintsIEEE Transactions on Image Processing, 1996
- Deformable templates using large deformation kinematicsIEEE Transactions on Image Processing, 1996
- Feature-based image metamorphosisACM SIGGRAPH Computer Graphics, 1992