DehazeGS: Seeing Through Fog with 3D Gaussian Splatting

Current novel view synthesis tasks primarily rely on high-quality and clear images. However, in foggy scenes, scattering and attenuation can sig- nificantly degrade the reconstruction and render- ing quality. Although NeRF-based dehazing re- construction algorithms have been developed, their use of deep fully connected neural networks and per-ray sampling strategies leads to high computa- tional costs. Moreover, NeRF’s implicit represen- tation struggles to recover fine details from hazy scenes. In contrast, recent advancements in 3D Gaussian Splatting achieve high-quality 3D scene reconstruction by explicitly modeling point clouds into 3D Gaussians. In this paper, we propose lever- aging the explicit Gaussian representation to ex- plain the foggy image formation process through a physically accurate forward rendering process. We introduce DehazeGS, a method capable of decom- posing and rendering a fog-free background from participating media using only muti-view foggy images as input. We model the transmission within each Gaussian distribution to simulate the forma- tion of fog. During this process, we jointly learn the atmospheric light and scattering coefficient while optimizing the Gaussian representation of the hazy scene. In the inference stage, we eliminate the ef- fects of scattering and attenuation on the Gaussians and directly project them onto a 2D plane to ob- tain a clear view. Experiments on both synthetic and real-world foggy datasets demonstrate that De- hazeGS achieves state-of-the-art performance in terms of both rendering quality and computational efficiency.