Adaptive dual-domain-guided semantics diffusion model for image defogging

Seeing through dense fog is a significant challenge in computer vision for attenuation of the target information, leading to differences in visual content. Image defogging works based on diffusion models still suffer from limitations such as loss of content and color information, as well as constraints in terms of long inference times. This paper introduces an adaptive dual-domain-guided semantics diffusion model for image defogging, which integrates the robust anti-interference capabilities of laser range-gated imaging with the exceptional feature learning abilities of diffusion models. Specifically, a deterministic data adaptive enhancer (DDAE) is utilized to analyze features in both the frequency and spatial domains, employing kernel-level features (such as blur intensity) extracted from blurry images. Subsequently, an enhanced-discrepancy-stochastic refinement (EDSR) strategy is employed to enable the conditional denoising diffusion model (CDDM) to perceive the non-ideal regions between foggy images and high-quality enhanced images, ultimately achieving high-fidelity image reconstruction. Extensive experiments have demonstrated that our method exhibits exceptional fog perception capabilities and outstanding defogging performance on indoor and outdoor laser range-gated imaging data with varying optical thicknesses (ranging from 0.5 to 3.0) as well as on color data. • The proposed framework combines DDAE and CDDM for laser range-gated image defogging in high OT scenarios (OT > 3.0). • DDAE integrates foggy data with clear data via dual-domain feature learning. It guides the diffusion model, enhancing defogging by focusing on affected areas for high-fidelity results. reconstruction. • We first apply laser range-gated camera and diffusion-based defogging model to variable optical thickness fog image dehazing, achieving impressive results on ITDF and O-ITDF datasets.