Scholarlink

<p>Composite weather degradation, particularly the spatial coupling of rain and haze, degrades image quality and undermines the reliability of outdoor vision systems in both 2D and 3D visual tasks. Motivated by the distinct frequency characteristics of these weather artifacts, we propose a task decomposition network (TDNet), a physically grounded image restoration framework for joint rain and haze removal. Central to our method is the degradation-aware comprehensive task decomposition (DCTD) strategy, which reformulates the challenging restoration problem into three coordinated subtasks guided by physics-informed inductive biases. Specifically, we first devise an implicit neural deraining (IND) module that exploits the inherent spectral bias of implicit neural representations to suppress high-frequency rain artifacts. Subsequently, we introduce a prior-adaptive dehazing (PAD) module that models the atmospheric scattering process in the feature space to remove low-frequency haze effects. Finally, a scene restoration module (SRM) aggregates degradation-free features to recover high-fidelity image content. Extensive experiments on synthetic and real-world benchmarks show that TDNet compares favorably with 18 representative baselines. Codes are available at <a href="https://github.com/cherrysherryplus/TDNet">https://github.com/cherrysherryplus/TDNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

TDNet: degradation-aware comprehensive task decomposition for joint rain and haze removal

  • 期刊论文

  • 发表日期：

    2026年7月8日

查看全文
  • Lei Liang,
  • Zhihua Chen,
  • Lei Dai,
  • Jiadan Gao,
  • Zhengran Xia,
  • Yunyi Zhang

摘要

Composite weather degradation, particularly the spatial coupling of rain and haze, degrades image quality and undermines the reliability of outdoor vision systems in both 2D and 3D visual tasks. Motivated by the distinct frequency characteristics of these weather artifacts, we propose a task decomposition network (TDNet), a physically grounded image restoration framework for joint rain and haze removal. Central to our method is the degradation-aware comprehensive task decomposition (DCTD) strategy, which reformulates the challenging restoration problem into three coordinated subtasks guided by physics-informed inductive biases. Specifically, we first devise an implicit neural deraining (IND) module that exploits the inherent spectral bias of implicit neural representations to suppress high-frequency rain artifacts. Subsequently, we introduce a prior-adaptive dehazing (PAD) module that models the atmospheric scattering process in the feature space to remove low-frequency haze effects. Finally, a scene restoration module (SRM) aggregates degradation-free features to recover high-fidelity image content. Extensive experiments on synthetic and real-world benchmarks show that TDNet compares favorably with 18 representative baselines. Codes are available at https://github.com/cherrysherryplus/TDNet.