Optical Flow via Locally Adaptive Fusion of Complementary Data Costs

Tae Hyun Kim, Hee Seok Lee, Kyoung Mu Lee
Department of ECE, ASRI, Seoul National University, 151-742, Seoul, Korea
International Computer Vision Conference (ICCV 2013), 2013


   title={Optical Flow via Locally Adaptive Fusion of Complementary Data Costs},

   author={Kim, Tae Hyun and Lee, Hee Seok and Lee, Kyoung Mu},



Download Download (PDF)   View View   Source Source   



Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. In this paper, in contrast to the conventional optical flow framework that uses a single or fixed data model, we study a novel framework that employs locally varying data term that adaptively combines different multiple types of data models. The locally adaptive data term greatly reduces the matching ambiguity due to the complementary nature of the multiple data models. The optimal number of complementary data models is learnt by minimizing the redundancy among them under the minimum description length constraint (MDL). From these chosen data models, a new optical flow estimation energy model is designed with the weighted sum of the multiple data models, and a convex optimization-based highly effective and practical solution that finds the optical flow, as well as the weights is proposed. Comparative experimental results on the Middlebury optical flow benchmark show that the proposed method using the complementary data models outperforms the state-of-the art methods.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: