Search papers, labs, and topics across Lattice.
UniBlendNet is introduced to address the limitations of existing Ambient Lighting Normalization (ALN) methods by improving global context modeling and spatial adaptivity. The framework unifies global illumination understanding via a UniConvNet module, multi-scale structure handling through a Scale-Aware Aggregation Module (SAAM), and region-adaptive refinement using a mask-guided residual mechanism. Experiments on the NTIRE ALN benchmark demonstrate that UniBlendNet outperforms IFBlend, achieving improved restoration quality and more natural results.
UniBlendNet achieves state-of-the-art ambient lighting normalization by adaptively correcting for spatially-varying illumination, leading to visually superior and more stable image restoration.
Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IFBlend, leverage frequency-domain priors to model illumination variations, but still suffer from limited global context modeling and insufficient spatial adaptivity, leading to suboptimal restoration in challenging regions. In this paper, we propose UniBlendNet, a unified framework for ambient lighting normalization that jointly models global illumination, multi-scale structures, and region-adaptive refinement. Specifically, we enhance global illumination understanding by integrating a UniConvNet-based module to capture long-range dependencies. To better handle complex lighting variations, we introduce a Scale-Aware Aggregation Module (SAAM) that performs pyramid-based multi-scale feature aggregation with dynamic reweighting. Furthermore, we design a mask-guided residual refinement mechanism to enable region-adaptive correction, allowing the model to selectively enhance degraded regions while preserving well-exposed areas. This design effectively improves illumination consistency and structural fidelity under complex lighting conditions. Extensive experiments on the NTIRE Ambient Lighting Normalization benchmark demonstrate that UniBlendNet consistently outperforms the baseline IFBlend and achieves improved restoration quality, while producing visually more natural and stable restoration results.