DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal
This addresses the challenge of incomplete and inconsistent flare removal in images, which is important for applications like visual object recognition and cross-modal semantic understanding, though it is incremental as it adapts state space models to a new task.
The paper tackled the problem of lens flare removal by proposing DeflareMamba, a hierarchical vision Mamba model that effectively removes various flare artifacts while maintaining contextual consistency, as demonstrated through extensive experiments.
Lens flare removal remains an information confusion challenge in the underlying image background and the optical flares, due to the complex optical interactions between light sources and camera lens. While recent solutions have shown promise in decoupling the flare corruption from image, they often fail to maintain contextual consistency, leading to incomplete and inconsistent flare removal. To eliminate this limitation, we propose DeflareMamba, which leverages the efficient sequence modeling capabilities of state space models while maintains the ability to capture local-global dependencies. Particularly, we design a hierarchical framework that establishes long-range pixel correlations through varied stride sampling patterns, and utilize local-enhanced state space models that simultaneously preserves local details. To the best of our knowledge, this is the first work that introduces state space models to the flare removal task. Extensive experiments demonstrate that our method effectively removes various types of flare artifacts, including scattering and reflective flares, while maintaining the natural appearance of non-flare regions. Further downstream applications demonstrate the capacity of our method to improve visual object recognition and cross-modal semantic understanding. Code is available at https://github.com/BNU-ERC-ITEA/DeflareMamba.