Department of Electrical Engineering (ISY)

Pushing the Limits for View Prediction in Video Coding

Jens Ogniewski, Per-Erik Forssén
VISAPP17, Porto, Portugal
12th International Conference on Computer Vision Theory and Applications (VISAPP'17)
February-March 2017

Abstract

More and more devices have depth sensors, making RGB+D video (colour+depth video) increasingly common. RGB+D video allows the use of depth image based rendering (DIBR) to render a given scene from different viewpoints, thus making it a useful asset in view prediction for 3D and free-viewpoint video coding.
In this paper we evaluate a multitude of algorithms for scattered data interpolation, in order to optimize the performance of DIBR for video coding. This also includes novel contributions like a Kriging refinement step, an edge suppression step to suppress artifacts, and a scale-adaptive kernel. Our evaluation uses the depth extension of the Sintel datasets. Using ground-truth sequences is crucial for such an optimization, as it ensures that all errors and artifacts are caused by the prediction itself rather than noisy or erroneous data. We also present a comparison with the commonly used mesh-based projection.

Full Paper

Portable document format file PDF ()
Proceedings from VISAPP 2017 will be accessible via the conference website.

---

Bibtex entry

@InProceedings{ogniewski17,
  author = 	 {Jens Ogniewski and Per-Erik Forss\'en},
  title = 	 {Pushing the Limits for View Prediction in Video Coding},
  booktitle =    {12th International Conference on Computer Vision Theory and Applications ({VISAPP'17})},
  year = 	 {2017},
  address = 	 {Porto, Portugal},
  month = 	 {February-March},
  publisher =    {Scitepress Digital Library}
  note =         {VR Project: Learnable Camera Motion Models, 2014-5928}
}