From Shadow Segmentation to Shadow Removal
arXiv:2008.00267
Abstract
The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets and hinders the possibility of training large-scale, robust shadow removal algorithms. We propose a shadow removal method that can be trained using only shadow and non-shadow patches cropped from the shadow images themselves. Our method is trained via an adversarial framework, following a physical model of shadow formation. Our central contribution is a set of physics-based constraints that enables this adversarial training. Our method achieves competitive shadow removal results compared to state-of-the-art methods that are trained with fully paired shadow and shadow-free images. The advantages of our training regime are even more pronounced in shadow removal for videos. Our method can be fine-tuned on a testing video with only the shadow masks generated by a pre-trained shadow detector and outperforms state-of-the-art methods on this challenging test. We illustrate the advantages of our method on our proposed video shadow removal dataset.
arXiv commentAccepted at ECCV 2020. All code, trained models, and data are available (soon) at: https://www3.cs.stonybrook. edu/~cvl/projects/FSS2SR/index.html
References in corpus (6)
- Which Training Methods for GANs do actually Converge?
- Direction-aware Spatial Context Features for Shadow Detection
- Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
- Improving Generalization and Stability of Generative Adversarial Networks
- Interactive Removal and Ground Truth for Difficult Shadow Scenes
- Geodesic Distance Histogram Feature for Video Segmentation