基于深度完整性先验与细粒度图像块策略的高精度二值图像分割
High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategy
把单目深度估计模型输出的伪深度当作「完整性先验」注入分割网络，用深度一致性损失约束分割结果，并用自适应图像块选择精修边界——这套思路可直接迁移到高分辨率抠图、显著目标检测等需要锐利边界的密集预测任务，且无需扩散模型即可逼近其精度。
原文依据 we leverage pseudo-depth information from monocular depth estimation models to obtain essential semantic understanding
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高精度二值图像分割（DIS）是一项从高分辨率图像中提取细粒度目标的任务。现有方法在效率与精度之间做取舍：非扩散方法速度快，但语义弱、空间先验不稳定，导致误检；基于扩散的方法借助强生成先验获得高精度，但计算代价高昂。在深度图中，完整目标表现为内部平滑、边界锐利的低方差区域，而背景由于不同深度处表面不连通，呈现混乱的高方差模式。我们将此称为深度完整性先验。受此启发，并注意到 DIS 目前缺乏深度图，我们利用单目深度估计模型提供的伪深度信息来获得必要的语义理解，从而快速揭示目标物体与背景之间的空间差异。为利用这一先验，我们提出先验引导的深度融合网络（PDFNet），它融合 RGB 与伪深度特征以实现深度感知的结构感知。我们进一步引入一种新的深度完整性先验损失，以在分割中强制深度一致性，并设计了一个带有自适应图像块选择的细粒度增强模块以锐化边界。值得注意的是，PDFNet 结合 DAM-v2 在参数量不到基于扩散方法一半的情况下达到了 SOTA（DIS-VD 上 F^ max _b 为 0.915，DIS-TE 上为 0.915）。
英文原文摘要 1442 字符
High-precision dichotomous image segmentation (DIS) is a task of extracting fine-grained objects from high-resolution images.Existing methods trade efficiency for accuracy: non-diffusion methods are fast but suffer from weak semantics and unstable spatial priors, causing false detections; diffusion-based methods offer high accuracy via strong generative priors but are computationally expensive.In depth maps, a complete object appears as a low variance region with a smooth interior and sharp boundaries, whereas the background exhibits a chaotic, high variance pattern due to disconnected surfaces at varying depths. We refer to this as the depth integrity-prior.Inspired by this, and noting that DIS currently lacks depth maps, we leverage pseudo-depth information from monocular depth estimation models to obtain essential semantic understanding, thereby rapidly revealing spatial differences across target objects and the background.To exploit this prior, we propose the Prior-guided Depth Fusion Network (PDFNet), which fuses RGB and pseudo-depth features for depth-aware structure perception. We further introduce a novel depth integrity-prior loss to enforce depth consistency in segmentation and a fine-grained enhancement module with adaptive patch selection to sharpen boundaries.Notably, PDFNet with DAM-v2 achieves SOTA (F^ max _b 0.915 on DIS-VD and 0.915 on DIS-TE) using less than half the params of diffusion-based methods.