Options in using graphics for evaluating correspondence algorithms

The paper discusses two options for evaluating the performance of stereo or motion correspondence algorithms in the context of vision-based driver assistance systems (i.e., in highly dynamic large-scale scenes). Assessing the significance of an evaluation scheme (which is always domain specific) is an issue not yet widely addressed by the research community. One option consists in modeling an existing environment and in identifying accurately the trajectory of the ego-vehicle carrying those cameras which capture sequences for correspondence analysis. Another option is given by physics-based rendering of a realistic 3D model of road scenario dynamics. The paper provides a discussion of both options.