HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

2026-04-04

AI Summary

This work addresses the complex degradation challenges in nighttime image dehazing—such as haze, halos, non-uniform illumination, color distortion, and sensor noise—by proposing a Transformer-enhanced multi-scale encoder-decoder architecture. The key innovation lies in a histogram-guided Transformer module that dynamically partitions features into range-based groups to model long-range dependencies, complemented by a frequency-adaptive feature refinement branch that jointly optimizes high- and low-frequency information to restore structural fidelity, suppress artifacts, and enhance fine details. Evaluated on the NTIRE 2026 Nighttime Image Dehazing Challenge involving 22 competing teams, the proposed method achieved first place, significantly outperforming existing approaches and demonstrating its effectiveness and robustness.

Abstract

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime dehazing. To address these challenges, we propose HistoFusionNet, a transformer-enhanced architecture tailored for nighttime image dehazing by combining histogram-guided representation learning with frequency-adaptive feature refinement. Built upon a multi-scale encoder-decoder backbone, our method introduces histogram transformer blocks that model long-range dependencies by grouping features according to their dynamic-range characteristics, enabling more effective aggregation of similarly degraded regions under complex nighttime lighting. To further improve restoration fidelity, we incorporate a frequency-aware refinement branch that adaptively exploits complementary low- and high-frequency cues, helping recover scene structures, suppress artifacts, and enhance local details. This design yields a unified framework that is particularly well suited to the heterogeneous degradations encountered in real nighttime hazy scenes. Extensive experiments and highly competitive performance of our method on the NTIRE 2026 Nighttime Image Dehazing Challenge benchmark demonstrate the effectiveness of the proposed method. Our team ranked 1st among 22 participating teams, highlighting the robustness and competitive performance of HistoFusionNet. The code is available at: https://github.com/heydarimo/Night-Time-Dehazing

Problem

• nighttime image dehazing
• haze
• non-uniform illumination
• color distortion
• sensor noise

Innovation

• Histogram-Guided Fusion
• Frequency-Adaptive Refinement
• Nighttime Image Dehazing
• Transformer-Enhanced Architecture
• Multi-Scale Feature Aggregation