Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal

TL;DR

This paper introduces DeflareMambav2, a novel lens flare removal method that uses prior-guided adaptive restoration and radial serialization to better handle region-dependent flare artifacts.

Contribution

It proposes a Flare Prior Network and a radial serialization strategy to improve targeted, region-aware lens flare removal over existing uniform processing methods.

Findings

Achieves state-of-the-art performance on flare removal tasks.

Reduces model complexity while maintaining high restoration quality.

Effectively preserves light sources and background details.

Abstract

Lens flares, caused by complex optical aberrations, severely degrade image quality especially in nighttime photography. Although recent restoration methods have made remarkable progress, most still rely on spatially uniform processing. They are failing to handle the region-dependent restoration demands of flare scenes, where saturated light sources should be preserved, flare artifacts removed, and background details recovered. To address this challenge, we propose DeflareMambav2, a prior-guided Mamba framework for lens flare removal. Specifically, we introduce a Flare Prior Network (FPN) to estimate flare priors and guide adaptive restoration. Besides, a novel radial serialization strategy breaks spatially homogeneous processing by performing flare-aware targeted sampling, and better supports long-range modeling in State Space Models (SSMs). Based on these priors, the backbone adopts a dual-level adaptive scheme. It explicitly preserves light-source regions to avoid over-processing, and applies curriculum-based restoration to the remaining contaminated areas while calibrating restoration intensity at the pixel level. Extensive experiments demonstrate that DeflareMambav2 achieves state-of-the-art performance with reduced parameter burden. Code is available at https://github.com/BNU-ERC-ITEA/DeflareMambav2.