Computer Graphics
TU Braunschweig

Integrating Approximate Depth Data into Dense Image Correspondence Estimation


Integrating Approximate Depth Data into Dense Image Correspondence Estimation

High-quality dense image correspondence estimation between two images is an essential prerequisite for many tasks in visual media production, one prominent example being view interpolation. Due to the ill-posed nature of the correspondence estimation problem, errors occur frequently for a number of problematic conditions, among them occlusions, large displacements and low-textured regions. In this paper, we propose to use approximate depth data from low-resolution depth sensors or coarse geometric proxies to guide the high-resolution image correspondence estimation. We counteract the effect of uncertainty in the prior by exploiting the coarse-to-fine image pyramid used in our estimation algorithm. Our results show that even with only approximate priors, visual quality improves considerably compared to an unguided algorithm or a pure depth-based interpolation.


Video

For more information, please contact the author via email.

Author(s):Kai Ruhl, Felix Klose, Christian Lipski, Marcus Magnor
Year:2012
Month:December
Type:Article in conference proceedings
Book:Proc. European Conference on Visual Media Production (CVMP)
Presented at:European Conference on Visual Media Production (CVMP)
Project(s): Image-space Editing of 3D Content  Reality CG 


@inproceedings{ruhl2012cvmp,
  title = {Integrating Approximate Depth Data into Dense Image Correspondence Estimation},
  author = {Ruhl, Kai and Klose, Felix and Lipski, Christian and Magnor, Marcus},
  booktitle = {Proc. European Conference on Visual Media Production ({CVMP})},
  volume = {9},
  pages = {1--6},
  month = {Dec},
  year = {2012}
}

Authors