15-06-2013, 12:18 PM
HIGH RESOLUTION ANIMATED SCENES FROM STILLS
RESOLUTION ANIMATED.doc (Size: 1.51 MB / Downloads: 16)
OVERVIEW OF THE SYSTEM
A single picture conveys a lot of information about the scene, but it rarely conveys the scene’s true dynamic nature. A video effectively does both but is limited in resolution. Off-the-shelf camcorders can capture videos with a resolution of 720 _ 480 at 30 fps, but this resolution pales in comparison to those for consumer digital cameras, whose resolution can be as high as 16 MPixels. What if we wish to produce a high resolution animated scene that reasonably reflects the true dynamic nature of the scene? Video textures are the perfect solution for producing arbitrarily long video sequences—if only very high resolution camcorders exist.
Our system is capable of generating compelling-looking animated scenes, but there is a major drawback: Their system requires a considerable amount of manual input. Furthermore, since the animation is specified completely manually, it might not reflect the true scene dynamics. We use a different tack that bridges video textures and system: We use as input a small collection of high resolution stills that (under-)samples the dynamic scene. This collection has both the benefit of the high resolution and some indication of the dynamic nature of the scene (assuming that the scene has some degree of regularity in motion). We are also motivated by a need for a more practical solution that allows the user to easily generate the animated scene. In this paper, we describe a scene animation system that can easily generate a video or video texture from a small collection of stills (typically, 10 to 20 stills are captured within 1 to 2 minutes, depending on the complexity of the scene motion).
ABSTRACT
Current techniques for generating animated scenes involve either videos (whose resolution is limited) or a single image (which requires a significant amount of user interaction). In this project, we describe a system that allows the user to quickly and easily produce a compelling-looking animation from a small collection of high resolution stills. Our system has two unique features. First, it applies an automatic partial temporal order recovery algorithm to the stills in order to approximate the original scene dynamics. The output sequence is subsequently extracted using a second-order Markov Chain model. Second, a region with large motion variation can be automatically decomposed into semiautonomous regions such that their temporal orderings are softly constrained. This is to ensure motion smoothness throughout the original region. The final animation is obtained by frame interpolation and feathering. Our system also provides a simple-to-use interface to help the user to fine-tune the motion of the animated scene. Using our system, an animated scene can be generated in minutes. We show results for a variety of scenes.
EXISTING SYSTEM:
The existing system has garnered a lot of attention is video texture, which reuses frames to generate a seamless video of arbitrary length.
Video textures work by figuring out frames in the original video that are temporally apart but visually close enough, so that jumping between such frames appears seamless.
This work was extended to produce video sprites, which permit high-level control of moving objects in the synthesized video. Unlike videos, the ordering of our input stills may not be 1D. Thus, we can only use partial orders as reference dynamics.
PROPOSED SYSTEM:
The proposed system is a scene animation system that can easily generate a video or video texture from a small collection of stills.
Our system first builds a graph that links similar images. It then recovers partial temporal orders among the input images and uses a second-order Markov Chain model to generate an image sequence of the video or video texture. Our system is designed to allow the user to easily fine-tune the animation.
SYSTEM ANALYSIS
Produce a compelling-looking animation scene from a small collection of high-resolution stills. This system has two unique features.
First, it applies an automatic partial temporal order recovery algorithm to the stills in order to approximate the original scene dynamics.
The output sequence is subsequently extracted using a second-order Markov Chain model.
A region with large motion variation can be automatically decomposed into semiautonomous regions such that their temporal orderings are softly constrained.
This is to ensure motion smoothness throughout the original region. Our system also provides a simple-to-use interface to help the user to fine-tune the motion of the animated scene.
CONCLUSION
• System is capable of generating high resolution animated videos from a small number of stills with very little user assistance
• This system also features user-friendly interfaces to allow the user to fine tune the motion quickly and effectively.