提出嵌套展开网络，实现真实场景隐匿物体分割的高鲁棒性
Nested Unfolding Network for Real-World Concealed Object Segmentation
- 采用双重展开结构，分离图像修复与分割任务
- 动态感知退化类型，提升在复杂真实场景下的分割精度
- 适合需要高鲁棒性的真实世界隐匿物检测应用
深度展开网络（DUN）通过迭代前景-背景分离推进了隐匿物体分割（COS）。然而现有基于DUN的方法（RUN）将背景估计与图像恢复耦合，目标冲突且需预设退化类型，不适用于真实场景。为此，我们提出嵌套展开网络（NUN），一种统一的实时世界COS框架。NUN采用DUN-in-DUN设计，在分割导向的展开网络（SODUN）每一阶段内嵌入抗退化展开网络（DeRUN），实现修复与分割解耦并支持相互优化。受视觉语言模型（VLM）引导，DeRUN动态推断退化语义并恢复高质量图像，无需显式先验；而SODUN执行可逆估计以精炼前景与背景。利用展开的多阶段特性，NUN通过图像质量评估选择最佳DeRUN输出用于后续阶段，自然引入自一致性损失以增强鲁棒性。大量实验表明，NUN在干净与退化基准上均达到领先性能。代码将开源。
原文摘要 · Abstract (English)
Deep unfolding networks (DUNs) have recently advanced concealed object segmentation (COS) by modeling segmentation as iterative foreground-background separation. However, existing DUN-based methods (RUN) inherently couple background estimation with image restoration, leading to conflicting objectives and requiring pre-defined degradation types, which are unrealistic in real-world scenarios. To address this, we propose the nested unfolding network (NUN), a unified framework for real-world COS. NUN adopts a DUN-in-DUN design, embedding a degradation-resistant unfolding network (DeRUN) within each stage of a segmentation-oriented unfolding network (SODUN). This design decouples restoration from segmentation while allowing mutual refinement. Guided by a vision-language model (VLM), DeRUN dynamically infers degradation semantics and restores high-quality images without explicit priors, whereas SODUN performs reversible estimation to refine foreground and background. Leveraging the multi-stage nature of unfolding, NUN employs image-quality assessment to select the best DeRUN outputs for subsequent stages, naturally introducing a self-consistency loss that enhances robustness. Extensive experiments show that NUN achieves a leading place on both clean and degraded benchmarks. Code will be released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。