# Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture

arXiv: https://arxiv.org/abs/2207.05605 · HTML: https://mlsanity.com/paper/2207.05605/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 12 of 12)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [DesnowNet: Context-Aware Deep Network for Snow Removal](https://mlsanity.com/paper/1708.04512/) (2017)
- [Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing](https://mlsanity.com/paper/1805.05308/) (2018)
- [NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing](https://mlsanity.com/paper/2003.12729/) (2020)
- [Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video](https://mlsanity.com/paper/1709.05943/) (2017)

## Built on by (most cited first, 9 of 9)

- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint](https://mlsanity.com/paper/2409.15739/) (2024)
- [Five A+ Network: You Only Need 9K Parameters for Underwater Image Enhancement](https://mlsanity.com/paper/2305.08824/) (2023)
- [Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation](https://mlsanity.com/paper/2303.16456/) (2023)
- [NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer](https://mlsanity.com/paper/2305.09533/) (2023)
- [VersaT2I: Improving Text-to-Image Models with Versatile Reward](https://mlsanity.com/paper/2403.18493/) (2024)
- [DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes](https://mlsanity.com/paper/2303.06905/) (2023)
- [RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement](https://mlsanity.com/paper/2302.12186/) (2023)
- [CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture](https://mlsanity.com/paper/2505.01882/) (2025)

## Abstract (arXiv)

In winter scenes, the degradation of images taken under snow can be pretty complex, where the spatial distribution of snowy degradation is varied from image to image. Recent methods adopt deep neural networks to directly recover clean scenes from snowy images. However, due to the paradox caused by the variation of complex snowy degradation, achieving reliable High-Definition image desnowing performance in real time is a considerable challenge. We develop a novel Efficient Pyramid Network with asymmetrical encoder-decoder architecture for real-time HD image desnowing. The general idea of our proposed network is to utilize the multi-scale feature flow fully and implicitly mine clean cues from features. Compared with previous state-of-the-art desnowing methods, our approach achieves a better complexity-performance trade-off and effectively handles the processing difficulties of HD and Ultra-HD images. The extensive experiments on three large-scale image desnowing datasets demonstrate that our method surpasses all state-of-the-art approaches by a large margin both quantitatively and qualitatively, boosting the PSNR metric from 31.76 dB to 34.10 dB on the CSD test dataset and from 28.29 dB to 30.87 dB on the SRRS test dataset.