Towards UAV Image Dehazing: A UAV Atmospheric Scattering Model, Benchmark, and Geometry-Aware Deep Unfolding Network
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of haze in drone images, which makes it hard to see distant details clearly. They created a new model called the UAV Atmospheric Scattering Model (UASM) to better represent how haze changes depending on the drone's height and angle. Using this model, they designed a new method called GP-DUN that combines physics knowledge with deep learning to remove haze more effectively. They also made a dataset with synthetic and real hazy drone images to test their method. Their experiments show that GP-DUN works better than previous methods for clearing haze in drone pictures.
UAV (Unmanned Aerial Vehicle)Haze removalAtmospheric scattering modelImage dehazingDeep unfolding networkTransmittanceGradient descentSynthetic datasetImage restorationPhysics-based modeling
Authors
Wenxuan Fang, Jiangwei Weng, Yu Zheng, Junkai Fan, Guangfa Wang, Xiang Chen, Jian Yang, Jun Li
Abstract
In UAV applications, haze significantly obscures distant details and weaken structural information, hindering the recovery of details. Current UAV scenarios still face two key challenges: (i) paired hazy/clean images from the real world are unobtainable, while the classical atmospheric scattering model is inadequate for modeling the spatially non-uniform haze in UAV imagery; (ii) existing dehazing methods struggle to remove the heavy haze accumulated in the upper regions of UAV images. To address these issues, we first propose a UAV Atmospheric Scattering Model (UASM), which explicitly incorporates flight altitude, viewing pitch, and extinction to characterize the non-uniform haze distribution in UAV imaging. Based on UASM, we develop a physics-driven dehazing framework, termed Geometry-aware Proximal Deep Unfolding Network (GP-DUN). Specifically, GP-DUN consists of three key modules: a Latent Geometry Estimator (LGE) that infers transmittance consistent with UAV imaging geometry, a Geometry-aware Gradient Descent Module (GeoGDM) that embeds UASM into the data-fidelity term and performs physics-consistent closed-form updates, and an Pooling-Expert Proximal Mapping Module (PE-PMM) that learns an implicit prior to restore textures and structures beyond the capability of explicit physical modeling. In addition, we further construct UASM-HazeSet, which provides controllable paired synthetic data together with 2,285 real UAV haze images for testing. Extensive experiments show that GP-DUN consistently outperforms existing methods on both UASM-HazeSet and real UAV haze benchmarks.