On the removal of shadows from images

By Graham David Finlayson, Steven D. Hordley, Cheng Lu, Mark Samuel Drew. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

695 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/49000038c77cc6b3f3318135126d22ad49b9cddb

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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Shadow Resistant Road Segmentation from a Mobile Monocular System (2007, methodology): “[4] show that under the assumptions of Planckian illumination, Lambertian surfaces and having three different narrow band sensors, it is possible to obtain a shadow–free color image.”
A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection (2020, methodology): “Existing methods detect shadows by developing physical models of color and illumination [6, 5], by using data-driven input images ground truths our method DSD [41] CVPR’2019 BDRAR [43] ECCV’2018 Figure 1: Shadow detection on two inputs with a soft shadow (the ﬁrst row) and multiple shadow regions…”
A Hybrid Vision-Map Method for Urban Road Detection (2017, background): “Another strategy is to remove shadows from the images [5] by converting the original RGB image into an illuminant invariant image.”
Overview of Environment Perception for Intelligent Vehicles (2017, methodology): “In [18], three different shadow-free images (1D, 2D, and 3D) were investigated according to simple constraints on lighting and cameras.”
Road Detection Based on Illuminant Invariance (2011, methodology): “This way, as a novelty, we propose to use the illuminant-invariant image introduced by Finlayson et al. [14] as the feature space.”
Illumination Invariant Imaging : Applications in Robust Vision-based Localisation , Mapping and Classification for Autonomous Vehicles (2014, methodology): “Both make use of the single-channel illumination invariant imaging approach presented in [21] for the purposes of removing shadows”
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal (2017, background): “[5, 7] provide the illumination invariant solutions that work well only on high quality images.”
Photo clip art (2007, methodology): “Applying GrabCut without shape prior results in fig.”
Multiscale shape and detail enhancement from multi-light image collections (2007, background): “We believe that it may be possible to adapt more sophisticated gradient-based shadow removal techniques [Weiss 2001; Finalyson et al. 2006] to produce better shadow-free base images.”
DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal (2017, methodology): “[9, 10] detect shadow edges by comparing a physically deduced illumination invariant image with the original RGB image, and then propose a series of gradient domain based methods for shadow removal.”
Ground truth dataset and baseline evaluations for intrinsic image algorithms (2009, background): “In particular, [5, 6] take advantage of the fact that most outdoor illumination changes lie in a two-dimensional subspace of log-RGB space.”
CrackTree: Automatic crack detection from pavement images (2012, methodology): “Compared to many classical shadow-removal algorithms (Finlayson et al., 2006, 2009; Arbel and Hel-Or, 2007), the geodesic shadow-removal algorithm 0167-8655/$ -see front matter Ó 2011 Elsevier B.V.”