HIGH RESOLUTION ANIMATED SCENES FROM STILLS

High resolution Animated Scenes from Stills

2. 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.

3. Description of the Problem

3.1 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.

Drawbacks:

·          Fully manual in traction.

·          Each and every process should be done by manually.

·          Ex.  Flash player.

3.2 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.

Merits:

• Reduce the user interaction
• Time complexity 
• User can give only collections of jpeg images. Based on the images we will get movie file for 1 or more than 2 mins.
• Simply conversion of Jpeg to Mpeg/AVI