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

2026-04-14

AI Summary

This work addresses the challenge of image degradation caused by complex spatially varying illumination, where existing methods exhibit limitations in global context modeling and spatial adaptability. The authors propose UniBlendNet, a unified framework that leverages a UniConvNet module to capture global illumination dependencies, integrates a scale-aware aggregation module (SAAM) for multi-scale structural fusion, and employs a mask-guided residual refinement mechanism for region-adaptive optimization. Evaluated on the NTIRE benchmark, the proposed method substantially outperforms the IFBlend baseline, achieving consistent improvements in visual naturalness, structural fidelity, and quantitative metrics, thereby enabling high-quality environmental illumination normalization.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Ambient Lighting Normalization
• global context modeling
• spatial adaptivity
• illumination variation
• image restoration

Innovation

• UniBlendNet
• ambient lighting normalization
• global context modeling
• multi-scale feature aggregation
• region-adaptive refinement