Star-Net: Improving Single Image Desnowing Model With More Efficient Connection and Diverse Feature Interaction

TL;DR

Star-Net is a novel single image desnowing network that employs efficient connection strategies and diverse feature interactions to effectively remove snow particles and fog, preserving image sharpness.

Contribution

The paper introduces a new network architecture with a Star type Skip Connection, a Multi-Stage Interactive Transformer, and a Degenerate Filter Module for improved snow removal.

Findings

Achieves state-of-the-art performance on three snow removal datasets.

Effectively preserves image sharpness after snow removal.

Handles complex snow shapes and reduces image distortion.

Abstract

Compared to other severe weather image restoration tasks, single image desnowing is a more challenging task. This is mainly due to the diversity and irregularity of snow shape, which makes it extremely difficult to restore images in snowy scenes. Moreover, snow particles also have a veiling effect similar to haze or mist. Although current works can effectively remove snow particles with various shapes, they also bring distortion to the restored image. To address these issues, we propose a novel single image desnowing network called Star-Net. First, we design a Star type Skip Connection (SSC) to establish information channels for all different scale features, which can deal with the complex shape of snow particles.Second, we present a Multi-Stage Interactive Transformer (MIT) as the base module of Star-Net, which is designed to better understand snow particle shapes and to address image distortion by explicitly modeling a variety of important image recovery features. Finally, we propose a Degenerate Filter Module (DFM) to filter the snow particle and snow fog residual in the SSC on the spatial and channel domains. Extensive experiments show that our Star-Net achieves state-of-the-art snow removal performances on three standard snow removal datasets and retains the original sharpness of the images.