MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images
arXiv:2005.10582
Abstract
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.
References in corpus (15)
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- DehazeNet: An End-to-End System for Single Image Haze Removal
- Semantic Foggy Scene Understanding with Synthetic Data
- Recurrent Models of Visual Attention
- DRAW: A Recurrent Neural Network For Image Generation
- Direction-aware Spatial Context Features for Shadow Detection
- Image De-raining Using a Conditional Generative Adversarial Network
- FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
- Rain Streak Removal for Single Image via Kernel Guided CNN
- Learning from synthetic photorealistic raindrop for single image raindrop removal
- NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining
- DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
- A Coarse-to-Fine Multi-stream Hybrid Deraining Network for Single Image Deraining
- An Effective Two-Branch Model-Based Deep Network for Single Image Deraining
- Gradient Information Guided Deraining with A Novel Network and Adversarial Training