Chromatic framework for vision in bad weather

By Srinivasa G. Narasimhan, Shree K. Nayar. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000

907 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/207993506ef1dd9c84fbda2cba93f8e3e9e49966

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Contrast Restoration of Weather Degraded Images (2003, background): “Narasimhan and Nayar [21] analyze color variations in the scene under different weather conditions based on the dichromatic atmospheric scattering model proposed in [24].”
A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior (2015, neutral): “In [21]–[23], Narasimhan et al.”
Benchmarking Single-Image Dehazing and Beyond (2017, background): “The atmospheric scattering model has been the classical description for the hazy image generation [6], [7], [8]:”
Instant dehazing of images using polarization (2001, background): “Computer vision methods have restored clear-day visibility of scenes using neither special radiation sources nor external knowledge about the scene structure or aerosols [11, 14].”
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing (2019, background): “The atmosphere scattering model [17, 20, 21] provides a simple approximation of the haze effect.”
Initial results in underwater single image dehazing (2010, background): “In order to resolve the ambiguity between the depth and the direct transmission, many existing dehazing techniques rely on additional hardware such as polarization filters [3, 4], additional information such as the depth of the scene [5], or multiple images captured under different conditions [2, 6]”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, background): “As the image dehazing problem is ill-posed, early approaches often require multiple frames to deal with this problem (Treibitz and Schechner 2009; Narasimhan and Nayar 2003, 2000; Schechner et al. 2001; Shwartz et al. 2006).”
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing (2019, methodology): “The atmosphere scattering model (Cartney 1976)(Narasimhan and Nayar 2000)(Narasimhan and Nayar 2002) provides a simple approximation of the haze effect, it is formulated as: Where I ( z ) is the observed hazy image, A is the global atmosphere light, and t ( z ) is the medium transmission map, J ( z…”
Single Image Haze Removal Using Dark Channel Prior (2011, background): “In computer vision and computer graphics, the model widely used to describe the formation of a hazy image is [2], [5], [10], [11]: IðxÞ ¼ JðxÞtðxÞ þ Að1 À tðxÞÞ; ð1Þ where I is the observed intensity, J is the scene radiance, A is the global atmospheric light, and t is the medium transmission…”
Non-local Image Dehazing (2016, methodology): “Generally, β is wavelength dependent and therefore t is different per color channel [11, 16].”
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing (2018, methodology): “Multiple images based methods overcome dehazing problem by obtaining changed atmospheric conditions from multiple images [21–23 , 36].”
Appearance-based face recognition and light-fields (2004, background): “Assuming that there is no absorption or scattering of light through the air [20], the light-field is actually only a 4D function, a 2D function of position defined over a 2D surface, and a 2D function of direction [13], [17].”
A Revised Underwater Image Formation Model (2018, background): “in the visible part of the electromagnetic spectrum becomes practically independent of wavelength [17, 29, 30, 32] (Fig.”