Motion-Compensated Frame Interpolation Based on Multihypothesis Motion Estimation and Texture Optimization
- Authors
- Jeong, Seong-Gyun; Lee, Chul; Kim, Chang-Su
- Issue Date
- 11월-2013
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Motion-compensated frame interpolation; frame rate up-conversion; multihypothesis motion estimation; exemplar-based texture synthesis; video segmentation
- Citation
- IEEE TRANSACTIONS ON IMAGE PROCESSING, v.22, no.11, pp.4497 - 4509
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE TRANSACTIONS ON IMAGE PROCESSING
- Volume
- 22
- Number
- 11
- Start Page
- 4497
- End Page
- 4509
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/101780
- DOI
- 10.1109/TIP.2013.2274731
- ISSN
- 1057-7149
- Abstract
- A novel motion-compensated frame interpolation (MCFI) algorithm to increase video temporal resolutions based on multihypothesis motion estimation and texture optimization is proposed in this paper. Initially, we form multiple motion hypotheses for each pixel by employing different motion estimation parameters, i.e., different block sizes and directions. Then, we determine the best motion hypothesis for each pixel by solving a labeling problem and optimizing the parameters. In the labeling problem, the cost function is composed of color, shape, and smoothness terms. Finally, we refine the motion hypothesis field based on the texture optimization technique and blend multiple source pixels to interpolate each pixel in the intermediate frame. Simulation results demonstrate that the proposed algorithm provides significantly better MCFI performance than conventional algorithms.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.