عنوان انگلیسی مقاله:
AI-GAN: Asynchronous interactive generative adversarial network for single image rain removal
ترجمه فارسی عنوان مقاله:
هوش مصنوعی -GAN: شبکه مواد تخاصمی ناهمزمان برای حذف باران با یک تصویر
Sciencedirect - Elsevier - Pattern Recognition, 100 (2020) 107143. doi:10.1016/j.patcog.2019.107143
Xin Jin, Zhibo Chen ∗, Weiping Li
Single image rain removal plays an important role in numerous multimedia applications. Existing algo- rithms usually tackle the deraining problem by the way of signal removal, which lead to over-smoothness and generate unexpected artifacts in de-rained images. This paper addresses the deraining problem from a completely different perspective of feature-wise disentanglement, and introduces the interactions and constraints between two disentangled latent spaces. Specifically, we propose an Asynchronous Interactive Generative Adversarial Network (AI-GAN) to progressively disentangle the rainy image into background and rain spaces in feature level through a two-branch structure. Each branch employs a two-stage synthe- sis strategy and interacts asynchronously by exchanging feed-forward information and sharing feedback gradients, achieving complementary adversarial optimization. This ‘adversarial’ is not only the ‘adversar- ial’ between the generator and the discriminator, but also means that the two generators are entangled, and interact with each other in the optimization process. Extensive experimental results demonstrate that AI-GAN outperforms state-of-the-art deraining methods and benefits various typical multimedia applica- tions such as Image/Video Coding, Action Recognition, and Person Re-identification.
Keywords: Feature-wise disentanglement | Asynchronous and interactive | Single image deraining | Complementary adversarial training