Joint Bilateral Upsampling

Cite This

Files in this item

Checksum: MD5:977392dfb1c1268fcbf597d39b78f7e7

KOPF, Johannes, Michael F. COHEN, Dani LISCHINSKI, Matt UYTTENDAELE, 2007. Joint Bilateral Upsampling. In: ACM Transactions on Graphics. 26(3), 96. Available under: doi: 10.1145/1275808.1276497

@article{Kopf2007Joint-5563, title={Joint Bilateral Upsampling}, year={2007}, doi={10.1145/1275808.1276497}, number={3}, volume={26}, journal={ACM Transactions on Graphics}, author={Kopf, Johannes and Cohen, Michael F. and Lischinski, Dani and Uyttendaele, Matt}, note={Article Number: 96} }

Kopf, Johannes eng Lischinski, Dani Lischinski, Dani Cohen, Michael F. Cohen, Michael F. Uyttendaele, Matt Attribution-NonCommercial-NoDerivs 2.0 Generic 2011-03-24T15:56:27Z First publ. in: ACM Transactions on Graphics 26 (2007), 3, Article No. 96 2007 Image analysis and enhancement tools such as tone mapping, colorization, stereo depth, and photomontage, require computing a solution (e.g., for exposure, chromaticity, disparity, labels) over the pixel grid. Computational and/or memory costs often require that a smaller solution be run over a down-sampled image. Although traditional upsampling methods can be used to interpolate the low resolution solution to the full resolution, these methods generally assume a smoothness prior for the interpolation.<br /><br />We demonstrate that in the cases, such as those above, where a high resolution image is available, it can be leveraged as a prior in the context of a joint bilateral upsampling procedure to produce a better high resolution solution. We show results for each of the applications above and compare them to traditional upsampling methods. 2011-03-24T15:56:27Z Uyttendaele, Matt Kopf, Johannes Joint Bilateral Upsampling application/pdf

Downloads since Oct 1, 2014 (Information about access statistics)

Joint_Bilateral_Upsampling.pdf 9289

This item appears in the following Collection(s)

Attribution-NonCommercial-NoDerivs 2.0 Generic Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 2.0 Generic

Search KOPS


My Account