Gradient domain high dynamic range compression

By Raanan Fattal, Dani Lischinski, Michael Werman. International Conference on Computer Graphics and Interactive Techniques, 2002

1,517 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2c7b0c853954b1c48f1a79ff0e922619cb5f76a7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Long-Term Image Boundary Prediction (2016, methodology): “7. We produce sharpened fused RGB predictions by taking the derivative of the RGB images and amplifying the gradients at the boundary locations (given by our extrapolated boundaries) in the spirit of [4]). This procedure improves the Tenengrad measure at t + 2 from 0.81 to 0.96 and at t + 4 from 0.4”
Color lines: image specific color representation (2004, methodology): “In order to readjust the dynamic range we use gamma correction or other methods for high dynamic range compression [4].”
Nonlinear image representation using divisive normalization (2008, methodology): “However, the independent adjustment of the transform coefficients often introduces artifacts such as ripples and halos around high-contrast features, and these need to be eliminated in a post-processing step [6, 14, 3].”
Color2Gray: salience-preserving color removal (2005, methodology): “Our work contributes to the growing trend in computer graphics of using change-based mappings for image representation and manipulation [Fattal et al. 2002; P´erez et al. 2003; Levin et al. 2004].”
Objective Quality Assessment of Tone-Mapped Images (2013, background): “To overcome this problem, an increasing number of tone mapping operators (TMOs) that convert HDR to LDR images have been developed, for examples [2]–[5].”
GP-GAN: Towards Realistic High-Resolution Image Blending (2017, neutral): “me registration errors or fast moving objects between the source images. Burt and Adelson [4] present a ﬁxing solution so-called multiband blending algorithm. Alternatively, gradient-based approaches [21,35,9,1,16,18,30] also address this problem by adjusting the differences in color and illuminatio”
Long-Term Image Boundary Extrapolation (2016, methodology): “We produce sharpened fused RGB predictions by taking the derivative of the RGB images and amplifying the gradients at the boundary locations (given by our extrapolated boundaries) in the spirit of [4]).”
Automated colour grading using colour distribution transfer (2007, methodology): “Matching the gradient of a picture has been addressed in different computer vision applications like high dynamic range compression [29]; the value of this idea has been thoroughly demonstrated by Pérez etal in [11].”
Exposure Fusion (2009, methodology): “Local tone mapping operators apply a spatially varying remap-ping [6, 8, 10, 15, 25, 29], i.e., the mapping changes for different regions in the image.”