UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization

TL;DR

UniBlendNet is a novel unified framework that improves ambient lighting normalization by modeling global, multi-scale, and region-specific illumination variations, leading to superior restoration quality.

Contribution

It introduces a comprehensive model combining global, multi-scale, and region-adaptive modules, advancing the state-of-the-art in ambient lighting normalization.

Findings

Outperforms baseline IFBlend on NTIRE benchmark

Produces more natural and stable illumination restoration

Effectively handles complex spatial lighting variations

Abstract

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.