Shadow Detection with Conditional Generative Adversarial Networks
Citations
758 citations
Cites methods from "Shadow Detection with Conditional G..."
...We compare our method with five deep shadow detection methods: JDR [31], DSC [10], DC-DSPF [37], scGAN [26], StackedCNN [30]....
[...]
252 citations
Cites background from "Shadow Detection with Conditional G..."
...GAN-based algorithms shows excellent performance in image generation [13, 14, 15, 16, 17]....
[...]
227 citations
222 citations
Cites background or methods from "Shadow Detection with Conditional G..."
...For detection part, we compare ST-CGAN with the stateof-the-art StackedCNN [52], cGAN [36] and scGAN [36]....
[...]
...Using ISTD Train Detection Aspects StackedCNN [52] cGAN [36] scGAN [36] ours...
[...]
...Using SBU Train Detection Aspects StackedCNN [52] cGAN [36] scGAN [36] ours...
[...]
...To evaluate the shadow detection performance quantitatively, we follow the commonly used terms [36] to compare the provided ground-truth masks and the predicted ones with the main evaluation metric, which is called Balance Error Rate (BER):...
[...]
...[36] presented the first application of adversarial training for shadow detection and developed a novel conditional GAN architecture with a tunable sensitivity parameter....
[...]
185 citations
Cites background or methods from "Shadow Detection with Conditional G..."
...input images ground truths our method DSC [6] scGAN [5] paCNN [24] stCNN [4] SRM [34] Amulet [35] PSPNet [36]...
[...]
...information to detect shadows from inputs, but just worked well for wide dynamic range images [5, 18]....
[...]
...And a generative adversarial network based shadow detector, called scGAN [5], was developed by formulating a conditional generator on input RGB images and learning to predict the corresponding shadow maps....
[...]
...DSC [6, 7] achieves a superior performance than other existing deep learning models [4, 5, 24] by analyzing the directional contexts to understand the global image semantics to infer shadows....
[...]
...We compare our method with five recent shadow detectors: DSC [6, 7], scGAN [5], stacked-CNN [4], patched-CNN [24] and Unary-Pairwise [19]....
[...]
References
111,197 citations
"Shadow Detection with Conditional G..." refers methods in this paper
...We train an scGAN with Stochastic Gradient Descent and the Adam solver [10], similar to [6]....
[...]
49,590 citations
28,225 citations
19,534 citations
"Shadow Detection with Conditional G..." refers methods in this paper
...The generator of our model is inspired by the U-Net architecture [26]....
[...]
...Figure 3: Generator’s architecture, a U-Net [26] based encoder-decoder with skip connections similar to [6]....
[...]
13,190 citations