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.
|
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/s11263-012-0579-7 | International Journal of Computer Vision |
Keywords | Field | DocType |
standard least-squares problem,region boundary,error-tolerant image compositing,classical poisson equation,gradient-domain technique,standard gradient-domain,color bleeding,new approach,composited image region,gradient-domain compositing,boundary location | Integrable system,Computer vision,Shadow,Alpha compositing,Image stitching,Poisson's equation,Linear system,Computer science,Color bleeding,Artificial intelligence,Compositing | Journal |
Volume | Issue | ISSN |
103 | 2 | 0920-5691 |
ISBN | Citations | PageRank |
3-642-15548-0 | 25 | 0.78 |
References | Authors | |
22 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael W. Tao | 1 | 225 | 11.75 |
Micah K. Johnson | 2 | 497 | 33.94 |
Sylvain Paris | 3 | 2494 | 113.53 |