Layered Image Warping with Post-texture Model

摘要

Image warping is one of the basic algorithms of image-based rendering. To eliminate the visual errors and reduce the redundant computations of traditional methods, a novel post-texture image warping model is proposed which mainly include equal-density mapping and texture reconstruction. With the new model, a layered image mapping (LIW) approach is proposed then. In LIW, reference pixels are firstly mapped to "equal density layers" which parallel the desired view and are stored in a bidirectional link list after some by-layer processing. By implementing texture rendering along the list eventually, the warping is transformed to a fast texture mapping process, which provides a considerable speedup. LIW is proved to be efficiently and effective by experiments.