Generative Adversarial Training for Weakly Supervised Cloud Matting
2019 IEEE/CVF International Conference on Computer Vision (ICCV)(2019)
摘要
The detection and removal of cloud in remote sensing images are essential for earth observation applications. Most previous methods consider cloud detection as a pixel-wise semantic segmentation process (cloud v.s. background), which inevitably leads to a category-ambiguity problem when dealing with semi-transparent clouds. We re-examine the cloud detection under a totally different point of view, i.e. to formulate it as a mixed energy separation process between foreground and background images, which can be equivalently implemented under an image matting paradigm with a clear physical significance. We further propose a generative adversarial framework where the training of our model neither requires any pixel-wise ground truth reference nor any additional user interactions. Our model consists of three networks, a cloud generator G, a cloud discriminator D, and a cloud matting network F, where G and D aim to generate realistic and physically meaningful cloud images by adversarial training, and F learns to predict the cloud reflectance and attenuation. Experimental results on a global set of satellite images demonstrate that our method, without ever using any pixel-wise ground truth during training, achieves comparable and even higher accuracy over other fully supervised methods, including some recent popular cloud detectors and some well-known semantic segmentation frameworks.
更多查看译文
关键词
recent popular cloud detectors,semantic segmentation frameworks,generative adversarial training,weakly supervised cloud,remote sensing images,earth observation applications,cloud detection,pixel-wise semantic segmentation process,cloud v.s. background,category-ambiguity problem,semitransparent clouds,mixed energy separation process,image matting paradigm,clear physical significance,generative adversarial framework,pixel-wise ground truth reference,cloud generator G,cloud discriminator D,cloud matting network F,cloud images,cloud reflectance,satellite images,fully supervised methods
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络