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.

翻译：单图像去雾仍然受限于高频细节丢失以及精确物理散射建模的困难。为解决这些问题，我们提出Fi-Gaussian，一种用于单图像去雾的频率感知隐式高斯泼溅网络。与依赖3D点云的显式渲染方法不同，我们的方法采用隐式高斯泼溅，在2D特征空间中将清晰图像的潜在分布自适应建模为连续表示。该网络的核心是频率感知隐式高斯泼溅模块，它在频域中解耦低频结构信息与高频纹理信息，然后通过具有复数权重的自适应高斯聚合来恢复精细细节。此外，我们引入了一个物理驱动的散射重归一化机制，在隐式高斯先验的指导下估计透射图与大气光。在多个基准数据集上的大量实验表明，Fi-Gaussian取得了最先进的定量性能，并生成了视觉上更优的去雾结果，验证了隐式高斯泼溅在低级视觉任务中的有效性。