Robust Aane Flow Estimation with Controlled Computation Cost

This paper addresses a classical problem-optical ow-for which we propose novel estimation algorithms based on robust regression. Another important aspect of our work is that we are concerned with the computational eeciency of our estimators, in the sense of maximizing its performance, for a chosen computation cost. This concern about eecient estimation appears often in active vision. It poses a much harder problem than estimation alone, and there seem to be very few theoretical results. After discussing the issue of performance assessment, we present a practical method for comparing the performance of diierent estimators, and the results obtained when comparing our algorithms with a more classical one.