BVI-Mamba: Video Enhancement Using a Visual State-Space Model for Low-Light and Underwater Environments
This work addresses the computational bottleneck of video enhancement for low-light and underwater environments, offering a more efficient solution for practical applications.
The paper proposes BVI-Mamba, a video enhancement framework using Visual State Space (VSS) models to reduce memory and computation, achieving superior performance over Transformer and convolution-based methods in low-light and underwater video enhancement.
Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection. Post-processing is typically required but can be time-consuming. AI-based tools for video enhancement also demand significantly more computational resources compared to image-based methods. This paper introduces a novel framework, Visual Mamba, designed to reduce memory usage and computational time by leveraging the Visual State Space (VSS) model. The framework consists of two modules: (i) a feature alignment module, where spatio-temporal displacement between input frames is registered in the feature space, and (ii) an enhancement module, where noise removal and brightness adjustment are performed using a UNet-like architecture, with all convolutional layers replaced by VSS blocks. Experimental results show that the Visual Mamba technique outperforms Transformer and convolution-based models in both low-light and underwater video enhancement tasks. Code is available on line at https://github.com/russellllaputa/BVI-Mamba.