Color lines: image specific color representation

By Ido Omer, Michael Werman. 2004

278 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Non-local Image Dehazing (2016, background): “This prior is based on the observation [13] that pixels in a hazefree image form color lines in RGB space.”
Color Constancy, Intrinsic Images, and Shape Estimation (2012, methodology): “We will build upon our previous model [1], but different forms of this idea have been used in intrinsic images techniques [23, 12], photometric stereo [24], shadow removal [25], and color representation [26].”
Ieee Transactions on Pattern Analysis and Machine Intelligence Shape, Illumination, and Reflectance from Shading (unknown): “We are not the first to explore global parsimony priors on reflectance: different forms of this idea have been used in intrinsic images techniques [15], photometric stereo [46], shadow removal [47], and color representation [48].”
Single Image Haze Removal Using Dark Channel Prior (2011, background): “According to [16], [17], the color line model holds for natural images.”
O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images (2018, methodology): “Fattal [16] introduces a method relying on the observation that the distributions of pixels in small natural image patches exhibit one-dimensional structures, named colorlines, in the RGB color space [33].”
Intrinsic Decompositions for Image Editing (2017, unknown): “This is often implemented by clustering lines of log-RGB pixel values, similar to the color lines model [OW04] (though not performed in the log-domain), or via entropy minimization [FDL04].”
Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, unknown): “[37].”
A Closed-Form Solution to Natural Image Matting (2006, background): “Furthermore, Omer and Werman [12] demonstrated that in many natural images the pixel colors in the RGB space tend to form a relatively small number of elongated clusters.”
NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images (2020, unknown): “[34].”