Video input driven animation (VIDA)

Sun, Dong; Jepson,; Fiume,

doi:10.1109/iccv.2003.1238319

Cited by 32 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, river and ocean wave image sequences are very challenging objects for stable estimation of dense optical flow. Using a harmonic oscillation equation, Sun et al [16] estimated one component of ocean wave motion in a video indirectly from a unidirectionally swaying yacht in a harbor with a manual setting. Thus, flow waves with various orientations were ignored.…”

Section: H Sakainomentioning

confidence: 99%

Motion estimation method based on physical properties of waves

Sakaino

2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

This paper presents a fluid flow estimation method for ocean/river waves, clouds, and smoke based on the physical properties of waves. Most of the previous optical flow methods based on fluid dynamics/mechanics estimate a smooth flow using a continuity equation and/or div-curl velocity constraint. However, abrupt or inhomogeneous image motion changes in such fluid-like images are not estimated well. In this paper, we assume that many fluid-like motion changes are due to wave phenomena that lead to a brightness change. Thus, a wave generation equation is applied with a two-step optimization. A novel constraint based on the velocity-frequency relationship equation and a wave statistical property are used. The results of experiments on synthetic and real image sequences show the validity of our method.

show abstract

Section: H Sakainomentioning

confidence: 99%

Motion estimation method based on physical properties of waves

Sakaino

2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Working on an inverse problem to ours, Sun et al [2003] propose a video-input driven animation (VIDA) system to extract physical parameters such as wind speed from real video footage. They then use these parameters to drive the physical simulation of synthetic objects to integrate them consistently with the source video.…”

Section: Related Workmentioning

confidence: 99%

“…Many natural motions can be viewed as harmonic oscillations [Sun et al 2003], and, indeed, hand-crafted superpositions of a small number of sinusoids have often been used to approximate natural phenomena for computer graphics. However, this simple approach has some limitations, as we discovered after experimenting with this idea.…”

Section: Stochastic Modeling Of Natural Phenomenamentioning

confidence: 99%

See 1 more Smart Citation

Animating pictures with stochastic motion textures

et al. 2005

View full text Add to dashboard Cite

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.

show abstract

“…The last step is relevant to the motion synthesis technique in computer graphics and animation. [27][28][29] Compared with finite element computer model simulations that require detailed information of the structure's physics, the video-based simulations implicitly incorporates these information in the modal model. In addition, the lowmodal-dimensional and decoupled nature of the modal model allows the proposed approach to directly solve only a few SDOF system equations in the modal domain to obtain the structural dynamic response, which is computationally efficient.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal video-domain high-fidelity simulation and realistic visualization of full-field dynamic responses of structures by a combination of high-spatial-resolution modal model and video motion manipulations

Yang

Dorn

Mancini

et al. 2018

Struct Control Health Monit

View full text Add to dashboard Cite

SummaryStructures with complex geometries, material properties, and boundary conditions exhibit spatially local dynamic behaviors. A high-spatial-resolution model of the structure is thus required for high-fidelity analysis, assessment, and prediction of the dynamic phenomena of the structure. The traditional approach is to build a highly refined finite element computer model for simulating and analyzing the structural dynamic phenomena based on detailed knowledge and explicit modeling of the structural physics such as geometries, materials properties, and boundary conditions. These physics information of the structure may not be available or accurately modeled in many cases, however. In addition, the simulation on the high-spatial-resolution structural model, with a massive number of degrees of freedom and system parameters, is computationally demanding. This study, on a proof-of-principle basis, proposes a novel alternative approach for spatiotemporal video-domain high-fidelity simulation and realistic visualization of full-field structural dynamics by an innovative combination of the fundamentals of structural dynamic modeling and the advanced video motion manipulation techniques.Specifically, a low-modal-dimensional yet high-spatial (pixel)-resolution (as many spatial points as the pixel number on the structure in the video frame) modal model is established in the spatiotemporal video domain with full-field modal parameters first estimated from line-of-sight video measurements of the operating structure. Then in order to simulate new dynamic response of the structure subject to a new force, the force is projected onto each modal domain, and the modal response is computed by solving each individual single-degree-of-freedom system in the modal domain. The simulated modal responses are then synthesized by the full-field mode shapes using modal superposition to obtain the simulated full-field structural dynamic response. Finally, the simulated structural dynamic response is embedded into the original video, replacing the original motion of the video, thus generating a new photo-realistic, physically accurate video that enables a --

show abstract

Video input driven animation (VIDA)

Abstract: Abstract

Cited by 32 publications

References 13 publications

Motion estimation method based on physical properties of waves

Motion estimation method based on physical properties of waves

Animating pictures with stochastic motion textures

Spatiotemporal video-domain high-fidelity simulation and realistic visualization of full-field dynamic responses of structures by a combination of high-spatial-resolution modal model and video motion manipulations

Contact Info

Product

Resources

About