Abstract | ||
---|---|---|
Wyner-Ziv coding of multiview images is an attractive solution because it avoids communications between individual cameras. To achieve good rate-distortion performance, the Wyner-Ziv decoder must reliably estimate the disparities between the multiview images. For the scenario where two reference images exist at the decoder, we propose a codec that effectively performs unsupervised learning of the two disparities between an image being Wyner-Ziv coded and the two reference images. The proposed two-disparity decoder disparity-compensates the two references images and generates side information more accurately than an existing one-disparity decoder. Experimental results with real multiview images demonstrate that the proposed codec achieves PSNR gains of 1-5 dB over the one-disparity codec. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICME.2008.4607513 | 2008 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-4 |
Keywords | Field | DocType |
image coding, data compression, stereo vision, disparity | Iterative reconstruction,Computer vision,Pattern recognition,Computer science,Stereopsis,Coding (social sciences),Unsupervised learning,Artificial intelligence,Decoding methods,Data compression,Codec,Encoding (memory) | Conference |
Citations | PageRank | References |
1 | 0.34 | 5 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
David M. Chen | 1 | 947 | 42.62 |
David P. Varodayan | 2 | 513 | 32.71 |
markus flierl | 3 | 350 | 77.81 |
Bernd Girod | 4 | 8988 | 1062.96 |