Compound Multi-branch Feature Fusion for Real Image Restoration
This work addresses the problem of limited generalization in image restoration for applications like autonomous cars, though it appears incremental as it builds on existing multi-branch architectures.
The paper tackles the lack of generalization in image restoration methods by proposing a multi-branch model inspired by the Human Visual System, achieving competitive performance on datasets for dehazing, deraindrop, and deblurring tasks.
Image restoration is a challenging and ill-posed problem which also has been a long-standing issue. However, most of learning based restoration methods are proposed to target one degradation type which means they are lack of generalization. In this paper, we proposed a multi-branch restoration model inspired from the Human Visual System (i.e., Retinal Ganglion Cells) which can achieve multiple restoration tasks in a general framework. The experiments show that the proposed multi-branch architecture, called CMFNet, has competitive performance results on four datasets, including image dehazing, deraindrop, and deblurring, which are very common applications for autonomous cars. The source code and pretrained models of three restoration tasks are available at https://github.com/FanChiMao/CMFNet.