Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

joint bilateral upsampling

Joint bilateral upsampling is an image processing technique that increases the resolution of a low-resolution data map, such as a depth, color, or tone mapping solution, by using a corresponding high-resolution reference image to guide the interpolation process. Extending the concept of bilateral filtering, the method calculates spatial distance weights across the low-resolution grid while deriving range or intensity difference weights from the high-resolution guide image. This edge-preserving mechanism prevents cross-boundary blurring and accurately transfers fine structural details and sharp boundaries from the full-resolution input into the upsampled result, enabling computationally expensive image analysis and enhancement tasks to be performed at lower resolutions and efficiently scaled up.

1 item

Joint bilateral upsampling

Joint bilateral upsampling

Johannes Kopf, Michael F. Cohen, Dani Lischinski, Matt Uyttendaele

OrganizationsMicrosoftThe Hebrew University of JerusalemUniversity of Konstanz

Why you should read this

Proposes a fast edge-preserving method that uses high-resolution guide images to accurately upsample low-resolution computational solutions in tone mapping, stereo depth, colorization, and segmentation tasks.

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.

Added

2026-09-25