International Journal of Computer Vision

, Volume 103, Issue 2, pp 178–189

Error-Tolerant Image Compositing

  • Michael W. Tao
  • Micah K. Johnson
  • Sylvain Paris
Article

DOI: 10.1007/s11263-012-0579-7

Cite this article as:
Tao, M.W., Johnson, M.K. & Paris, S. Int J Comput Vis (2013) 103: 178. doi:10.1007/s11263-012-0579-7

Abstract

Gradient-domain compositing is an essential tool in computer vision and its applications, e.g., seamless cloning, panorama stitching, shadow removal, scene completion and reshuffling. While easy to implement, these gradient-domain techniques often generate bleeding artifacts where the composited image regions do not match. One option is to modify the region boundary to minimize such mismatches. However, this option may not always be sufficient or applicable, e.g., the user or algorithm may not allow the selection to be altered. We propose a new approach to gradient-domain compositing that is robust to inaccuracies and prevents color bleeding without changing the boundary location. Our approach improves standard gradient-domain compositing in two ways. First, we define the boundary gradients such that the produced gradient field is nearly integrable. Second, we control the integration process to concentrate residuals where they are less conspicuous. We show that our approach can be formulated as a standard least-squares problem that can be solved with a sparse linear system akin to the classical Poisson equation. We demonstrate results on a variety of scenes. The visual quality and run-time complexity compares favorably to other approaches.

Keywords

Gradient-domain compositingVisual masking

Supplementary material

11263_2012_579_MOESM1_ESM.zip (13.3 mb)
(ZIP 13.3 MB)

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  • Michael W. Tao
    • 1
  • Micah K. Johnson
    • 2
  • Sylvain Paris
    • 3
  1. 1.University of CaliforniaBerkeleyUSA
  2. 2.Massachusetts Institute of TechnologyCambridgeUSA
  3. 3.Adobe Systems, Inc.CambridgeUSA