# DehazeGS: Seeing Through Fog with 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2501.03659 · HTML: https://mlsanity.com/paper/2501.03659/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 7 Jan 2025.

## Builds on (most cited first, 18 of 18)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [Unsupervised Single Image Dehazing Using Dark Channel Prior Loss](https://mlsanity.com/paper/1812.07051/) (2018)
- [ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering](https://mlsanity.com/paper/2305.02103/) (2023)
- [DehazeNeRF: Multiple Image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fields](https://mlsanity.com/paper/2303.11364/) (2023)
- [Dehazing-NeRF: Neural Radiance Fields from Hazy Images](https://mlsanity.com/paper/2304.11448/) (2023)
- [SpikeGS: Learning 3D Gaussian Fields from Continuous Spike Stream](https://mlsanity.com/paper/2409.15176/) (2024)

## Built on by (most cited first, 4 of 4)

- [Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2505.01235/) (2025)
- [NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather](https://mlsanity.com/paper/2603.27228/) (2026)
- [Dehaze-GaussianImage: Zero-Shot Dehazing via Efficient 2D Gaussian Splatting Representation](https://mlsanity.com/paper/2606.16163/) (2026)
- [Fi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing](https://mlsanity.com/paper/2606.16168/) (2026)

## Abstract (arXiv)

Current novel view synthesis methods are typically designed for high-quality and clean input images. However, in foggy scenes, scattering and attenuation can significantly degrade the quality of rendering. Although NeRF-based dehazing approaches have been developed, their reliance on deep fully connected neural networks and per-ray sampling strategies leads to high computational costs. Furthermore, NeRF's implicit representation limits its ability to recover fine-grained details from hazy scenes. To overcome these limitations, we propose learning an explicit Gaussian representation to explain the formation mechanism of foggy images through a physically forward rendering process. Our method, DehazeGS, reconstructs and renders fog-free scenes using only multi-view foggy images as input. Specifically, based on the atmospheric scattering model, we simulate the formation of fog by establishing the transmission function directly onto Gaussian primitives via depth-to-transmission mapping. During training, we jointly learn the atmospheric light and scattering coefficients while optimizing the Gaussian representation of foggy scenes. At inference time, we remove the effects of scattering and attenuation in Gaussian distributions and directly render the scene to obtain dehazed views. Experiments on both real-world and synthetic foggy datasets demonstrate that DehazeGS achieves state-of-the-art performance. visualizations are available at https://jz-y-cn.github.io/DehazeGS/