Frame interpolation and bidirectional prediction of video using compactly encoded optical-flow fields and label fields

Ravi Krishnamurthy, John W. Woods, Pierre Moulin

Research output: Contribution to journalArticlepeer-review

Abstract

We consider the problems of motion-compensated frame interpolation (MCFI) and bidirectional prediction in a video coding environment. These applications generally require good motion estimates at the decoder. In this paper, we use a multiscale optical-flow-based motion estimator that provides smooth, natural motion fields under bit-rate constraints. These motion estimates scale well with change in temporal resolution and provide considerable flexibility in the design and operation of coders and decoders. In the MCFI application, this estimator provides excellent interpolated frames that are superior to those of conventional motion estimators, both visually and in terms of peak signal-to-noise ratio (PSNR). We also consider the effect of occlusions in the bidirectional prediction application and introduce a dense label field that complements our motion estimator. This label field enables us to adaptively weight the forward and backward predictions and gives us substantial visual and PSNR improvements in the covered/uncovered regions of the sequence.

Original languageEnglish (US)
Pages (from-to)713-726
Number of pages14
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume9
Issue number5
DOIs
StatePublished - 1999

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Frame interpolation and bidirectional prediction of video using compactly encoded optical-flow fields and label fields'. Together they form a unique fingerprint.

Cite this