Joint bilateral upsampling
Joint bilateral upsampling
复制标题
DOI：
10.1145/1275808.1276497
复制
发表时间：
2007-07
期刊：
影响因子：
--
通讯作者：
J. Kopf;Michael F. Cohen;Dani Lischinski;M. Uyttendaele
中科院分区：
文献类型：
--
作者：
J. Kopf;Michael F. Cohen;Dani Lischinski;M. Uyttendaele
诸如色调映射、着色、立体深度和照片蒙太奇的图像分析和增强任务通常需要计算解决方案（例如，用于曝光、色度、视差、标签）。计算和内存成本通常要求在下采样图像上运行较小的解决方案。尽管通用上采样方法可用于将低分辨率解内插到全分辨率，但这些方法通常假设内插的平滑度优先。我们证明，在诸如上述那些的情况下，可用的高分辨率输入图像可以在联合双边上采样过程的上下文中被用作先验，以产生更好的高分辨率解决方案。我们展示了上述每个应用的结果，并将其与传统的上采样方法进行了比较。
Image analysis and enhancement tasks such as tone mapping, colorization, stereo depth, and photomontage, often require computing a solution (e.g., for exposure, chromaticity, disparity, labels) over the pixel grid. Computational and memory costs often require that a smaller solution be run over a downsampled image. Although general purpose 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. We demonstrate that in cases, such as those above, the available high resolution input image may 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.