Image metamorphosis using snakes and free-form deformations

Abstract

This paper presents new solutions to the following three problems in image morphing: feature specification, warp generation, and transition control. To reduce the burden of feature specification, we first adopt a computer vision technique called snakes. We next propose the use of multilevel free-form deformations (MFFD) to achieve C 2 -continuous and one-to-one warps among feature point pairs.The resulting technique, based on B-spline approximation, is simpler and faster than previous warp generation methods. Finally, we simplify the MFFD method to construct C 2 -continuous surfaces for deriving transition functions to control geometry and color blending.

Interactive surface decomposition for polyhedral morphing

“…The set of algorithms can be classified into those that operate on raster images [4,13,30,47,48] and those that operate on vector-based or geometric representations [19,40,42,45]. Feature-based image morphing can be achieved by energy minimization [40] or featurebased constraints [42].…”

“…Beier and Neely presented an elegant feature-based approach [4]. The features may be points or lines [4,44] or to snakes [30].…”

“…Mappings that have been used include (bi)linear mappings [4,44] and spline-based mappings or free-form deformations [30] in conjunction with a weighting function that effectively controls the range over which a feature has influence. Ranjan and Fournier [37] presented an approach which uses circles to partition the objects.…”

A New Control Curve Method for Image Deformation

“…Lee presented the free grid deformation method [5], which can achieve the deformation by the image parameterization using binary cubic interpolation spline, but it need to align the register grid according to image characteristics with the control point spline, and it is Not easy to operate. Beier and Neely improved the free grid deformation technology by using a set of line segments to control the deformation, which is very comfortable to use [4].…”

Earth Mover’s Morphing: Topology-Free Shape Morphing Using Cluster-Based EMD Flows

“…In the early stages of morphing research, correspondences between geometric primitives including points, lines, and curves were manually given and various types of warping functions were proposed, such as mesh warping [7], field morphing [8], the radial basis function [9], thin plate spline [10], energy minimizationbased function [11], and Multilevel Free-Form Deformation (MFFD) [12] [13]. During the middle stages, methods for automatic correspondence were proposed to reduce burdens of user input [14] [15] [16] [17] [18].…”