# CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture

arXiv: https://arxiv.org/abs/2505.01882 · HTML: https://mlsanity.com/paper/2505.01882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 75 references that are in the map.
- First posted on arXiv 3 May 2025.

## Builds on (most cited first, 29 of 29)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [DesnowNet: Context-Aware Deep Network for Snow Removal](https://mlsanity.com/paper/1708.04512/) (2017)
- [Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning](https://mlsanity.com/paper/1904.05050/) (2019)
- [Gated Fusion Network for Single Image Dehazing](https://mlsanity.com/paper/1804.00213/) (2018)
- [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018)
- [STAR: A Structure and Texture Aware Retinex Model](https://mlsanity.com/paper/1906.06690/) (2019)
- [DAWN: Vehicle Detection in Adverse Weather Nature Dataset](https://mlsanity.com/paper/2008.05402/) (2020)
- [SCNet: Training Inference Sample Consistency for Instance Segmentation](https://mlsanity.com/paper/2012.10150/) (2020)
- [Quaternion Convolutional Neural Networks for Heterogeneous Image Processing](https://mlsanity.com/paper/1811.02656/) (2018)
- [An All-in-One Network for Dehazing and Beyond](https://mlsanity.com/paper/1707.06543/) (2017)
- [Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond](https://mlsanity.com/paper/1711.06787/) (2017)
- [A Survey on Rain Removal from Video and Single Image](https://mlsanity.com/paper/1909.08326/) (2019)
- [Progressive Feature Fusion Network for Realistic Image Dehazing](https://mlsanity.com/paper/1810.02283/) (2018)
- [SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing](https://mlsanity.com/paper/2208.09703/) (2022)
- [Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture](https://mlsanity.com/paper/2207.05605/) (2022)
- [Incorporating Lambertian Priors into Surface Normals Measurement](https://mlsanity.com/paper/2107.07192/) (2021)
- [QSAM-Net: Rain streak removal by quaternion neural network with self-attention module](https://mlsanity.com/paper/2208.04346/) (2022)

## Abstract (arXiv)

Images used in real-world applications such as image or video retrieval, outdoor surveillance, and autonomous driving suffer from poor weather conditions. When designing robust computer vision systems, removing adverse weather such as haze, rain, and snow is a significant problem. Recently, deep-learning methods offered a solution for a single type of degradation. Current state-of-the-art universal methods struggle with combinations of degradations, such as haze and rain-streak. Few algorithms have been developed that perform well when presented with images containing multiple adverse weather conditions. This work focuses on developing an efficient solution for multiple adverse weather removal using a unified quaternion neural architecture called CMAWRNet. It is based on a novel texture-structure decomposition block, a novel lightweight encoder-decoder quaternion transformer architecture, and an attentive fusion block with low-light correction. We also introduce a quaternion similarity loss function to preserve color information better. The quantitative and qualitative evaluation of the current state-of-the-art benchmarking datasets and real-world images shows the performance advantages of the proposed CMAWRNet compared to other state-of-the-art weather removal approaches dealing with multiple weather artifacts. Extensive computer simulations validate that CMAWRNet improves the performance of downstream applications such as object detection. This is the first time the decomposition approach has been applied to the universal weather removal task.