BlockNet: A Deep Neural Network for Block-Based Motion Estimation Using Representative Matching
Department of Electrical Engineering, Pohang University of Science and Technology, San 31, Hyoja-dong, Nam-gu, Pohang, Gyungbuk 37673, Korea
LG Display Co., Ltd., E2 Block LG Science Park, 30, Magokjungang 10-ro, Gangseo-gu, Seoul 07796, Korea
Author to whom correspondence should be addressed.
The authors contribute equally.
Symmetry 2020, 12(5), 840; https://doi.org/10.3390/sym12050840
Received: 25 April 2020 / Revised: 15 May 2020 / Accepted: 17 May 2020 / Published: 20 May 2020
Owing to the limitations of practical realizations, block-based motion is widely used as an alternative for pixel-based motion in video applications such as global motion estimation and frame rate up-conversion. We hereby present BlockNet, a compact but effective deep neural architecture for block-based motion estimation. First, BlockNet extracts rich features for a pair of input images. Then, it estimates coarse-to-fine block motion using a pyramidal structure. In each level, block-based motion is estimated using the proposed representative matching with a simple average operator. The experimental results show that BlockNet achieved a similar average end-point error with and without representative matching, whereas the proposed matching incurred 18% lower computational cost than full matching.