Fi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose a new method called Fi-Gaussian to improve single image dehazing. Their approach models clear images using a special kind of math called implicit Gaussian splatting to better capture both general shapes and fine details in images. They separate easy-to-see parts from tiny textures and use physics knowledge about light scattering to enhance the image. Tests show that their method works better than others in removing haze from pictures.
single image dehazingGaussian splattingfrequency domainhigh-frequency detailstransmission mapatmospheric lightimplicit representationphysical scatteringimage restoration
Authors
Yuhan Chen, Ying Fang, Guofa Li, Wenxuan Yu, Yicui Shi, Kunyang Huang, Wenbo Chu, Keqiang Li
Abstract
Single image dehazing continues to be hindered by the loss of high-frequency details and the difficulty of accurate physical scattering modeling. To address these issues, we propose Fi-Gaussian, a frequency-aware implicit Gaussian splatting network for single image dehazing. Unlike explicit rendering methods that rely on 3D point clouds, our method employs implicit Gaussian splatting to adaptively model the underlying distribution of clear images as a continuous representation in 2D feature space. The core of the network is a frequency-aware implicit Gaussian splatting module, which decouples low-frequency structural information and high-frequency texture information in the frequency domain and then performs adaptive Gaussian aggregation with complex-valued weights to recover fine details. In addition, a physics-driven scattering renormalization mechanism is introduced to estimate the transmission map and atmospheric light under the guidance of implicit Gaussian priors. Extensive experiments on multiple benchmark datasets demonstrate that Fi-Gaussian achieves state-of-the-art quantitative performance and produces visually superior dehazed results, validating the effectiveness of implicit Gaussian splatting for low-level vision tasks.