Motion-based video retargeting with optimized crop-and-warp

Yu-Shuen Wang*, Hui Chih Lin, Olga Sorkine, Tong Yee Lee

*Corresponding author for this work

Research output: Contribution to journalArticle

78 Scopus citations

Abstract

We introduce a video retargeting method that achieves high-quality resizing to arbitrary aspect ratios for complex videos containing diverse camera and dynamic motions. Previous content-aware retargeting methods mostly concentrated on spatial considerations, attempting to preserve the shape of salient objects in each frame by removing or distorting homogeneous background content. However, sacrificeable space is fundamentally limited in video, since object motion makes foreground and background regions correlated, causing waving and squeezing artifacts. We solve the retargeting problem by explicitly employing motion information and by distributing distortion in both spatial and temporal dimensions. We combine novel cropping and warping operators, where the cropping removes temporally-recurring contents and the warping utilizes available homogeneous regions to mask deformations while preserving motion. Variational optimization allows to find the best balance between the two operations, enabling retargeting of challenging videos with complex motions, numerous prominent objects and arbitrary depth variability. Our method compares favorably with state-of-the-art retargeting systems, as demonstrated in the examples and widely supported by the conducted user study.

Original languageEnglish
Article number90
JournalACM Transactions on Graphics
Volume29
Issue number4
DOIs
StatePublished - 13 Sep 2010

Keywords

  • Cropping
  • Optimization
  • Spatial and temporal coherence
  • Video retargeting
  • Warping

Fingerprint Dive into the research topics of 'Motion-based video retargeting with optimized crop-and-warp'. Together they form a unique fingerprint.

  • Cite this