Scinovex
articleTop 10% cited

Gradient domain high dynamic range compression

ACM Transactions on Graphics · 2002 · Vol. 21(3) · pp. 249–256
Raanan FattalDani LischinskiMichael Werman

Abstract

We present a new method for rendering high dynamic range images on conventional displays. Our method is conceptually simple, computationally efficient, robust, and easy to use. We manipulate the gradient field of the luminance image by attenuating the magnitudes of large gradients. A new, low dynamic range image is then obtained by solving a Poisson equation on the modified gradient field. Our results demonstrate that the method is capable of drastic dynamic range compression, while preserving fine details and avoiding common artifacts, such as halos, gradient reversals, or loss of local contrast. The method is also able to significantly enhance ordinary images by bringing out detail in dark regions.

Image Enhancement TechniquesComputer Graphics and Visualization TechniquesAdvanced Vision and ImagingHigh dynamic rangeRendering (computer graphics)LuminanceComputer scienceTone mappingDynamic rangeRange (aeronautics)Computer visionHigh-dynamic-range imagingArtificial intelligence

Funding

  • Israel Science Foundation
Citations
759
FWCI
11.91
field-weighted impact
References
27
Percentile
99%
vs. same field & year
Citations per year
Cited by
Edge-preserving decompositions for multi-scale tone and detail manipulation
ACM Transactions on Graphics · 2008 · 1,447 citations
Interactive digital photomontage
ACM Transactions on Graphics · 2004 · 834 citations
Joint bilateral upsampling
ACM Transactions on Graphics · 2007 · 818 citations
Poisson image editing
ACM Transactions on Graphics · 2003 · 1,720 citations
Guided Image Filtering
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2012 · 5,295 citations
References
Scale-space and edge detection using anisotropic diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence · 1990 · 11,953 citations
Citation Network

How this paper connects to the literature. Drag to explore, click any node to open that paper.