Animating pictures with stochastic motion textures

Abstract

a) Japanese Temple (b) Harbor (c) Boat Studio (d) Argenteuil (e) Sunflowers Figure 1 Sample input images we animate using our technique. The first two pictures are photographs of a Japanese Temple (a) and a harbor (b). The paintings shown in (c) and (d) are Claude Monet's The Boat Studio and The Bridge at Argenteuil. We also apply our method to Van Gogh's Sunflower (e) to animate the flowers. (The last three paintings are courtesy of WebMuseum, AbstractIn this paper, we explore the problem of enhancing still pictures with subtly animated motions. We limit our domain to scenes containing passive elements that respond to natural forces in some fashion. We use a semi-automatic approach, in which a human user segments the scene into a series of layers to be individually animated. Then, a "stochastic motion texture" is automatically synthesized using a spectral method, i.e., the inverse Fourier transform of a filtered noise spectrum. The motion texture is a time-varying 2D displacement map, which is applied to each layer. The resulting warped layers are then recomposited to form the animated frames. The result is a looping video texture created from a single still image, which has the advantages of being more controllable and of generally higher image quality and resolution than a video texture created from a video source. We demonstrate the technique on a variety of photographs and paintings.

Realistic animation of interactive trees

“…The simplified mechanical method ignores the global mechanical structure of a tree and represents tree sways by a driven harmonic oscillator [2,[5][6][7] or by a static mechanical response [8][9][10]. Shinya and Fournier [5] create wind model by using the power spectra of wind field and they use independent damped harmonic oscillator to model the motion of branches.…”

“…Shinya and Fournier [5] create wind model by using the power spectra of wind field and they use independent damped harmonic oscillator to model the motion of branches. Chuang et al [6] and Habel et al [2] introduce a spectral method that includes the motion spectrum of a damped harmonic oscillator. Hu et al [7] use a 1/f β noise and the simplified mechanical model to animate the deformation of leaves in wind field.…”

“…A common geometrical model to represent a branch is that of cantilever beams which has been described in [2,[5][6][7]. Shinya and Fournier [5] and Chuang et al [6] assume for simplicity that the cantilever beam is a uniform thin beam. Habel et al [2] improve the beam model to a tapered one and use a length-correction method to avoid stretching when subjected to a large load.…”

“…Studies of the effect of branches and leaves on damping ratios [6,17,20] suggest that a branch with abundance of sub-branches and leaves may have a greater damping ratio than a branch with few branches and leaves. Thus, we use an empirical equation to approximate the damping ratio of the j th branch of a tree:…”

A Simple Method to Animate Vegetation in Images Using Simulation-Guided Grid-Based Warping

“…For example, in Figure 9, on the left, when the grass is swaying in wind, its shape is deforming, on the right, the tree crown moves like a continuum. However, existing methods of animating vegetation in images ( [1], [2]) mainly handle only tree type vegetation with branches whose motions usually exhibit rigid property. Existing methods mainly focus on modeling single elements such as grass blades, leaves and branches, instead of addressing explicitly the overall appearance of the movements of a vegetation field, which we believe can be handled in a simpler and more efficient manner.…”