MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images
Rain severely hampers the visibility of scene objects when images are captured through glass in heavily rainy days. We observe three intriguing phenomenons that, 1) rain is a mixture of raindrops, rain streaks and rainy haze; 2) the depth from the camera determines the degrees of object visibility, where objects nearby and faraway are visually blocked by rain streaks and rainy haze, respectively; and 3) raindrops on the glass randomly affect the object visibility of the whole image space. We for the first time consider that, the overall visibility of objects is determined by the mixture of rain (MOR). However, existing solutions and established datasets lack full consideration of the MOR. In this work, we first formulate a new rain imaging model; by then, we enrich the popular RainCityscapes by considering raindrops, named RainCityscapes++. Furthermore, we propose a multi-branch attention generative adversarial network (termed an MBA-RainGAN) to fully remove the MOR. The experiment shows clear visual and numerical improvements of our approach over the state-of-the-arts on RainCityscapes++. The code and dataset will be available.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkRain RemovalSimilar Papers 제목 키워드 기반
Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
Current approaches have made great progress on image-to-image translation tasks benefiting from the success of image synthesis methods especially generative adversarial networks (GANs). However, existing methods are limi…
Generative Adversarial NetworkImage GenerationImage-to-Image TranslationTranslationCross-View Exocentric to Egocentric Video Synthesis
Cross-view video synthesis task seeks to generate video sequences of one view from another dramatically different view. In this paper, we investigate the exocentric (third-person) view to egocentric (first-person) view v…
Generative Adversarial NetworkVideo GenerationSemi-DerainGAN: A New Semi-supervised Single Image Deraining Network
Removing the rain streaks from single image is still a challenging task, since the shapes and directions of rain streaks in the synthetic datasets are very different from real images. Although supervised deep deraining n…
Rain RemovalSingle Image DerainingA Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds
In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner. To overcome the difficulty of capt…
Generative Adversarial NetworkIncremental Generative Occlusion Adversarial Suppression Network for Person ReID
Person re-identification (re-id) suffers from the significant challenge of occlusion, where an image contains occlusions and less discriminative pedestrian information. However, certain work consistently attempts to desi…
Data AugmentationPerson Re-Identification