Single-image shadow detection and removal using paired regions

By Ruiqi Guo, Qieyun Dai, Derek Hoiem. Computer Vision and Pattern Recognition, 2011

343 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4ad2440354917f159f557faf5ab8d918c6bc0504

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Jian Yang
2. P. Heng
3. Luc Van Gool
4. Xiang-Yang Li
5. Jitendra Malik
6. Lei Zhang
7. Li Fei-Fei
8. Scott Satkin

Citations in the corpus

• Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal (2017, methodology): “Guo [11] and Gong [8] fail to detect shadow accurately, thus both of their predictions are incomplete especially in shadow regions.”
• 3DNN: 3D Nearest Neighbor (2014, methodology): “It should be noted that our geometry estimation algorithm is one of many recent works which rely on accurate viewpoint estimation Fouhey et al. (2012); Gupta et al. (2011).”
• Shading Annotations in the Wild (2017, neutral): “, hard shadow detection and removal [22, 17]).”
• A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection (2020, methodology): “We make comparison with 10 recent shadow detectors including DSDNet [41], DC-DSPF [37], BDRAR [43], AD-Net [24], DSC [12], ST-CGAN [35], patched-CNN [8], scGAN [28], stacked-CNN [33], and Unary-Pairwise [7].”