Image and Video Retargetting by Darting

TR Image
Stretching a densely textured image using a trellis that opens gaps in regions with low color variation and fills them with texture from elsewhere in the image.

This paper considers the problem of altering an image by imperceptibly adding or removing pixels, for example, to fit a differently shaped frame with minimal loss of interesting content. We show how to construct a family of convex programs that suitably rearrange pixels while minimizing image artifacts and distortions. We call this "darting" on analogy to a tailor's darts-small edits are discreetly distributed throughout the fabric of the image. We develop a reduction to integer dynamic programming on edit trellises, yielding fast algorithms. One- and two-pass variants of the method have 0(1) per-pixel complexity. Of the many edits that darting supports, five are demonstrated here: image retargeting to smaller aspect ratios: adding or moving or removing scene objects while preserving image dimensions: image expansion with gaps filled by a rudimentary form of texture synthesis; temporal video summarization by "packing" motion in time; and an extension to spatial video retargetting that avoids motion artifacts by preserving optical flow.


  • Related News & Events

    •  NEWS   ICIAR 2009: publication by Matthew E. Brand
      Date: July 7, 2009
      Where: International Conference on Image Analysis and Recognition (ICIAR)
      MERL Contact: Matthew Brand
      • The paper "Image and Video Retargetting by Darting" by Brand, M.E. was presented at the International Conference on Image Analysis and Recognition (ICIAR)