Adaptive layer extraction for image based rendering
Jesse Berent, Pier Luigi Dragotti, Mike Brookes · IEEE International Workshop on Multimedia Signal Processing (MMSP) · 2009
Image based rendering is a promising way to produce arbitrary views of a scene using images instead of object models. However, depth variations and occlusions cause blurring in the rendered images. The solution is to use some geometrical information in order to steer the interpolation filters according to the depth. The level of detail of this geometry is often predetermined. In this paper, we present a method for extracting depth layers in the presence of occlusions for image based rendering. Moreover, we show how the layer extraction can be made to estimate depth layers in an adaptive manner, based on the spectral analysis of the plenoptic function. The rendering system therefore automatically adapts the number of depth layers based on the scene and the spacing of the sample cameras.
Cited by 8 works. doi:10.1109/mmsp.2009.5293298
Authors
References
- Mean shift: a robust approach toward feature space analysis
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
- Light field rendering
- The lumigraph
- The Plenoptic Function and the Elements of Early Vision
- High-quality video view interpolation using a layered representation
- Layered depth images
- Unstructured lumigraph rendering
- Plenoptic sampling
- High-quality video view interpolation using a layered representation