Image based rendering deals with the generation of virtual views from a small set of real reference images. Much research on this area has been conducted by the computer vision community over the last decade. Currently, most problems involved in this technology are well understood and there exist several well-established algorithms to render virtual views from perspectivelly different images of the same scene. However, most work has been oriented towards high-accuracy disparity estimation to produce high-quality virtual images, often using sophisticated purpose-built hardware accelerators to achieve real-time results. In this paper two disparity estimators with different complexity degrees are described and used to examine how much disparity inaccuracies influence image rendering quality. The objective of this study is to design software-based image synthesis in real-time on conventional PC platforms. Basically, this work looks at the opposite end of the cost-complexity curve by making very restrained demands to the disparity estimator. It is empirically shown that in many cases the effect of disparity accuracy in the quality of virtual views is almost imperceptible and that for many applications requiring real-time processing reasonable good results can be achieved with less computational cost.
