Name
Abstract | ||
|---|---|---|
This paper compares two-dimensional (2-D) and three-dimensional (3-D) object modeling in terms of their capabilities and performance (peak signal-to-noise-ratio and visual image quality) for very low bitrate video coding. We show that 2-D object-based coding with affine/perspective transformations and triangular mesh models can simulate almost all capabilities of 3-D object-based approaches using wireframe models at a fraction of the computational cost. Furthermore, experiments indicate that a 2-D mesh-based coder-decoder performs favorably compared to the new H.263 standard in terms of visual quality |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/76.564115 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
data compression,decoding,knowledge based systems,transform coding,video codecs,video coding,2D mesh based coder-decoder,2D object-based codecs,2D object-based coding,3D object-based codecs,H.263 standard,affine/perspective transformations,computational cost,experiments,knowledge based approach,peak signal to noise ratio,performance,three-dimensional object-based video compression,triangular mesh models,two-dimensional object-based video compression,very low bitrate video coding,visual image quality,wireframe models | Affine transformation,Computer vision,Computer science,Transform coding,Image processing,Image quality,Object model,Artificial intelligence,Data compression,Signal compression,Triangle mesh | Journal |
Volume | Issue | ISSN |
7 | 2 | 1051-8215 |
Citations | PageRank | References |
2 | 0.47 | 22 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| A Murat Tekalp | 1 | 1893 | 201.68 |
| Y. Altunbasak | 2 | 1042 | 85.73 |
| G. Bozdagi | 3 | 221 | 21.93 |