![]() |
|
||
Bilateral Functions for Global Motion ModelingWen-Yan Daniel Lin1, Ming-Ming Cheng2, Jiangbo Lu1, Hongsheng Yang3, Minh N. Do4, and Philip Torr2 1Advanced Digital Sciences Center, Singapore 2Oxford University, UK 3University of North Carolina at Chapel Hill, USA 4University of Illinois at Urbana-Champaign, USA Abstract. This paper proposes modeling motion in a bilateral domain that augments spatial information with the motion itself. We use the bilateral domain to reformulate a piecewise smooth constraint as continuous global modeling constraint. The resultant model can be robustly computed from highly noisy scattered feature points using a global minimization. We demonstrate how the model can reliably obtain large numbers of good quality correspondences over wide baselines, while keeping outliers to a minimum. LNCS 8692, p. 341 ff. lncs@springer.com
|