Data-driven model gradual deformation method

Abstract

The invention discloses a data-driven model gradual deformation method, comprising the following steps of: S1, inputting model library with same mesh topologies; S2, performing up-sampling on models in the model library in the S1 through using a method of keeping the local rigidity of the model; S3, clustering the model library which is subjected to the up-sampling to get a deformation subspace; S4, providing an initial model S and a terminal point model T which need to be treated by gradual deformation, and according to the corresponding relation, performing the deformation under the condition of keeping local details to obtain models S' and T'; S5, solving a quadratic integer optimization to obtain a model sequence M' from S' to T'; S6, by rigid body transformation of each surface patch on the model in the M' on a migration model sequence and solving one poisson equation, obtaining a group of new model sequence from S to T; and S7, obtaining a final gradual deformation sequence by means of Gauss interpolation of the local rigid energy. By using the method disclosed by the invention, a relatively true and nature model gradual deformation sequence can be generated.

Description

technical field [0001] The invention relates to the technical field of digital media, in particular to a data-driven model gradual change method. Background technique [0002] The model gradient technology can generate a series of gradual intermediate models according to a given pair of start and end models. The key to the model gradient technology is to be able to generate a natural model gradient sequence that conforms to objective laws. [0003] Traditional methods use interpolation to generate intermediate gradient sequences by selecting different parameter spaces. When the starting model and the ending model are geometrically very close, linear interpolation can produce an ideal gradient sequence, but if the geometric difference is large, direct linear interpolation of the coordinates will produce self-intersection, distortion, etc. unreasonable gradient effect. Alex et al.'s work "as-rigid-as possible shape interpolation" in 2004 is to decompose the radial transforma...

AI Technical Summary

Problems solved by technology

But since the physical properties of the models vary, these physics-based methods can still produce unreasonable gradient effects or even cases where the models self-intersect

[0005] When generating an intermediate gradient sequence model given a starting model and a termination model, in existing technologies, methods that are no

Images