Example Based Processing For Image And Video Synthesis

Markov random fields;Image-based rendering;Learning from example;Filter approximation;Function approximation

Haro, Antonio ; Computing

University:Georgia Institute of Technology

Department:Computing

关键词: Markov random fields;    Image-based rendering;    Learning from example;    Filter approximation;    Function approximation;   

Others  :  https://smartech.gatech.edu/bitstream/1853/5283/1/haro_antonio_200311.pdf

美国|英语

来源: SMARTech Repository

【 摘 要 】

The example based processing problem can be expressed as: "Given an example of an image or video before and after processing, apply a similar processing to a new image or video".Our thesis is that there are some problems where a single general algorithm can be used to create varieties of outputs, solely by presenting examples of what is desired to the algorithm. This is valuable if the algorithm to produce the output is non-obvious, e.g. an algorithm to emulate an example painting's style. We limitour investigations to example based processing of images, video, and 3D models as these data types are easy to acquire and experiment with.We represent this problem first as a texture synthesis influenced sampling problem, where the idea is to form feature vectors representative of the data and then sample them coherently tosynthesize a plausible output for the new image or video. Grounding the problem in this manner is useful as both problems involve learning the structure of training data under some assumptions to sample it properly. We then reduce the problem to a labeling problem to perform example based processing in a more generalized and principled manner than earlier techniques. This allows us to perform a different estimation of what the outputshould be by approximating the optimal (and possibly not known) solution through a different approach.