一种前景背景联合学习的单幅图像去雪模型
CSTR:
作者:
作者单位:

(1.哈尔滨工程大学 信息与通信工程学院,哈尔滨 150001; 2.海能达通信股份有限公司,广东 深圳 518057)

作者简介:

包玉刚(1986—),男,博士研究生;赵旦峰(1961—),男,教授,博士生导师

通讯作者:

赵旦峰,zhaodanfeng@hrbeu.edu.cn

中图分类号:

TP391.4

基金项目:

中国电子科技集团公司第五十四研究所校企合作项目(KY10800210062)


A single-image desnowing model with joint foreground-background learning
Author:
Affiliation:

(1.College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China; 2.Hytera Science & Technology Co., Ltd., Shenzhen 518057, Guangdong, China)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为解决当前单幅图像去雪模型普遍仅关注前景雪花建模与移除,忽视图像背景信息,导致整体还原精度不高的问题,提出一种前景背景联合学习的单幅图像去雪模型。首先,设计一种基于逐深度卷积的双尺度幻像特征模块,在增强雪花与背景细节表征能力的同时,有效缓解过拟合风险;其次,提出前景背景联合学习机制,在雪花建模过程中引入背景语义信息,引导模型更全面地理解图像结构与场景上下文;最后,构建双边长短时特征融合单元,促进前景与背景特征间的充分融合与交互,以进一步提升图像复原的质量与稳定性。 在Snow100K、CSD两个公开基准数据集上进行有效性验证。实验结果表明,前景背景联合学习的单幅图像去雪模型在RPSN、SSSIM指标上均优于对比模型,展现出更强的鲁棒性、泛化能力与处理复杂雪景图像的能力。所提模型有效弥补了现有模型在背景建模方面的不足,在实际应用场景中具备较高的实用价值。

    Abstract:

    To address the issue that current single-image desnowing models generally only focus on the modeling and removal of foreground snowflakes while neglecting image background information, resulting in low overall restoration accuracy, a single-image snow removal model based on joint foreground-background learning is proposed. Firstly, a dual-scale phantom feature module based on depth wise convolution is designed to enhance the representation ability of snowflakes and background details while effectively mitigating the risk of overfitting; Secondly, a joint foreground-background learning mechanism is proposed to introduce background semantic information into the snowflake modeling process, guiding the model to comprehensively understand the image structure and scene context; Finally, a bilateral long-short-term feature fusion unit is constructed. To promote full fusion and interaction between foreground and background features,which further improves the quality and stability of image restoration. Effectiveness was evaluated on two public benchmark datasets Snow100K and CSD. The results show that the proposed model outperforms existing mainstream models in terms of RPSN, SSSIM, demonstrating stronger robustness, generalization ability, and ability to process complex snow scene images. This model effectively compensates for the background modeling deficiencies in existing models and has high practical value for real-world scenarios.

    参考文献
    相似文献
    引证文献
引用本文

包玉刚,孙鹏飞,赵旦峰,贾皓翔.一种前景背景联合学习的单幅图像去雪模型[J].哈尔滨工业大学学报,2026,58(9):37. DOI:10.11918/202410026

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-10-12
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-10-11
  • 出版日期:
文章二维码