| Sponsor | Irfan Essa |
| Area | Computational Perception |
Problem
Problem Scope: How to use video to render novel video with both novel content and novel viewpoint. This extends the Image-based Rendering to Video, by analyzing time.
See the following projects from http://www.cc.gatech.edu/cpl/projects/#Rendering
Image-based Method for Generating Motion Blur. An approach that allows for generating motion blur as a video-based post-process. Applications shown for blurring stop-motion footage and for real video. Learning video processing by example: We approximate the output of an arbitrary video processing algorithm based on a pair of input and output exemplars. Our algorithm relies on learning the mapping between the input and output exemplars to model the processing that has taken place. Multi-dimensional Texture Synthesis using Graph Cuts: A patch-based method for texture synthesis in multiple dimensions. An algorithm for finding optimal seams between input and output texture (for a given texture placement/offset) is developed. Our technique allows iterative refinement of already generated textures. Rendering Skin: Fine scale skin structure has traditionally been ignored when rendering human skin. This technique adds the detail that is missing, and increases its photo-realism significantly. VideoTextures: Develop a new pictorial medium that is in-between photographs (static) and video (with a well-defined begin and an end). Videotextures allows generation of infinitely long videos from a finite set of frames. This tecnhique can be used for video-based rendering and video-based animation.
Also see http://www.cc.gatech.edu/cpl/projects/artstyling/ and http://www.cc.gatech.edu/cpl/projects/examplebased/
Come talk to me and we will identify a short duration effort.