Degradation Modeling for Restoration-Enhanced Object Detection in Adverse Weather Scenes

Object detection is widely applied in fields such as scene perception and intelligent driving. However, interfered by degradations such as rain, haze, and snow, object detection in adverse weather conditions pose significant challenges. Mainstream methods usually fail to take into account the object detection of degraded images and cannot effectively handle them. In this paper, we present a Restoration-enhanced object detection network for adverse weather scenes enabled by Degradation Modeling, dubbed RDMNet. Firstly, to capture more potential information of degraded images, we incorporate the idea of restoration into the detection network, thus forming a dual branch network. Secondly, to improve the network's adaptability for different weather types, we propose to model the degradation of degraded images and learn its multi-scale degradation representations to guide the feature transformation in both restoration and detection branches. Finally, to facilitate the cross-task integration of restoration and detection branches, we develop a multi-scale bi-directional feature fusion block and propose a restoration weight decay training strategy. Extensive experiments in rain, haze, and snow weathers demonstrate that our RDMNet outperforms the recent object detection approaches.