API: Empowering Generalizable Real-World Image Dehazing via Adaptive Patch Importance Learning

2026-01-05

arXiv.org

AI Summary

This work addresses the limited generalization of existing image dehazing methods in complex real-world hazy scenes, primarily caused by insufficient training data and the high diversity of haze density distributions. To overcome these challenges, we propose an adaptive block importance learning framework that innovatively integrates Automatic Haze Generation (AHG), a Density-aware Haze Removal (DHR) module, and a Multi-Negative Contrastive Dehazing (MNCD) loss, jointly optimized in both spatial and frequency domains. This approach significantly enhances the model’s adaptability to varying haze distributions and achieves state-of-the-art performance across multiple real-world dehazing benchmarks, demonstrating superior quantitative metrics and visual quality.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Real-world image dehazing is a fundamental yet challenging task in low-level vision. Existing learning-based methods often suffer from significant performance degradation when applied to complex real-world hazy scenes, primarily due to limited training data and the intrinsic complexity of haze density distributions.To address these challenges, we introduce a novel Adaptive Patch Importance-aware (API) framework for generalizable real-world image dehazing. Specifically, our framework consists of an Automatic Haze Generation (AHG) module and a Density-aware Haze Removal (DHR) module. AHG provides a hybrid data augmentation strategy by generating realistic and diverse hazy images as additional high-quality training data. DHR considers hazy regions with varying haze density distributions for generalizable real-world image dehazing in an adaptive patch importance-aware manner. To alleviate the ambiguity of the dehazed image details, we further introduce a new Multi-Negative Contrastive Dehazing (MNCD) loss, which fully utilizes information from multiple negative samples across both spatial and frequency domains. Extensive experiments demonstrate that our framework achieves state-of-the-art performance across multiple real-world benchmarks, delivering strong results in both quantitative metrics and qualitative visual quality, and exhibiting robust generalization across diverse haze distributions.

Problem

• real-world image dehazing
• generalization
• haze density distribution
• limited training data

Innovation

• Adaptive Patch Importance
• Automatic Haze Generation
• Density-aware Haze Removal
• Multi-Negative Contrastive Dehazing
• Real-world Image Dehazing