A spatio-temporal auto regressive model for frame rate upconversion

  • Authors:

  • Yongbing Zhang;Debin Zhao;Xiangyang Ji;Ronggang Wang;Wen Gao

  • Affiliations:

  • Department of Computer Science, Harbin Institute of Technology, Harbin, China;Department of Computer Science, Harbin Institute of Technology, Harbin, China;Broadband Networks and Digital Media Laboratory, Department of Automation, Tsinghua University, Beijing, China;France Telecom Research and Development, Beijing Company Ltd, Beijing, China;Key Laboratory of Machine Perception, School of Electronic Engineering and Computer Science, Peking University, Beijing, China

  • Venue:
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a spatio-temporal auto regressive (STAR) model for frame rate upconversion. In the STAR model, each pixel in the interpolated frame is approximated as the weighted combination of a sample space including the pixels within its two temporal neighborhoods from the previous and following original frames as well as the available interpolated pixels within its spatial neighborhood in the current tobe-interpolated frame. To derive accurate STAR weights, an iterative self-feedback weight training algorithm is proposed. In each iteration, first the pixels of each training window in the interpolated frames are approximated by the sample space from the previous and following original frames and the to-be-interpolated frame. And then the actual pixels of each training window in the original frame are approximated by the sample space from the previous and following interpolated frames and the current original frame with the same weights. The weights of each training window are calculated by jointly minimizing the distortion between the interpolated frames in the current and previous iterations as well as the distortion between the original frame and its interpolated one. Exteusive simulation results demonstrate that the proposed STAR model is able to yield the interpolated frames with high performance in terms of both subjective and objective qualities.