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

Tian Ye, Sixiang Chen, Yun Liu, Yi Ye, Jinbin Bai, Erkang Chen; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 366-381

In winter scenes, the degradation of images taken under snow can be pretty complex, where the spatial distribution of snowy degradation varies from image to image. Recent methods adopt deep neural networks to recover clean scenes from snowy images directly. 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 to 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. The source code is available at \href https://github.com/Owen718/Towards-Real-time-High-Definition-Image-Snow-Removal-Efficient-Pyramid-Network https://github.com/Owen718/Towards-Real-time-High-Definition-Image-Snow-Removal-Efficient-Pyramid-Network