Abstract The traditional complete dual-branch structure is effective for semantic segmentation tasks. However, it redundant in some sense. Moreover, the simple additive fusion of features from two branches may not achieve satisfactory performance. To alleviate these problems, this paper we propose an efficient compact interactive network (CIDNet) real-time segmentation. Specifically, first buil...

The generation process of low-light images is fundamentally complicated due to their multi-factorial degradation. Many previous methods favorably developed a multi-branch network for impressive performance. However, the complex structures networks always incur large computational cost and hinders applicability in those resource-limited settings. To alleviate these issues, this letter novel ligh...

Due to the absorption and scattering effects of light propagating through water, underwater images inevitably suffer from severe degradation, such as color casts losses detail. Many existing deep learning-based methods have demonstrated superior performance for image enhancement (UIE). However, accurate correction detail restoration still present considerable challenges UIE. In this work, we de...