DORS：用于密集场景中基于扩散的目标移除的动态注意力路由
DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes
浏览论文内容
中文总结 AI 辅助
针对密集场景目标移除中因语义干扰致移除不完整的问题，提出基于动态注意力路由机制的DORS框架，含实例过滤注意力和上下文引导路由组件，经实验验证其性能优于现有方法。
中文摘要 AI 辅助
目标移除旨在通过掩码指定的方式消除目标对象，同时保持与周围区域的视觉一致性。现有方法通常依赖周围区域的上下文信息。然而，在密集场景中，周围区域包含与移除目标视觉相似的实例，这种依赖往往会导致语义干扰，导致移除不完整。该问题源于注意力空间中的错误信息传播，其中掩码查询由于自注意力中的全局相似性匹配而倾向于与这些实例对齐。为应对这一挑战，我们提出了一种用于密集场景的基于扩散的目标移除框架DORS，它基于动态注意力路由机制构建，包括两个互补组件：实例过滤注意力（IFA），通过动态构建的掩码引导注意力约束抑制来自相似实例的误导性语义信息；上下文引导路由（CGR），动态路由互补场景信息以保持视觉一致性。我们还引入了DOR-Bench，这是一个针对密集场景中目标移除量身定制的基准。大量实验表明，DORS优于现有方法，特别是在减少移除不完整和重复伪影方面。代码将在该https网址提供。
英文摘要
Object removal aims to eliminate target objects specified by a mask while preserving visual consistency with the surrounding regions. Existing methods typically rely on contextual information from surrounding regions. However, in dense scenes where the surrounding regions contain instances visually similar to the removal target, such reliance often leads to semantic interference, resulting in incomplete removal. This problem arises from erroneous information propagation in the attention space, where masked queries tend to align with such instances due to global similarity matching in self-attention. To address this challenge, we propose a Diffusion-based Object Removal framework for dense Scenes, dubbed DORS, built upon a Dynamic Attention Routing mechanism comprising two complementary components: Instance-Filtered Attention (IFA), which suppresses misleading semantic information from similar instances through dynamically constructed mask-guided attention constraints, and Context-Guided Routing (CGR), which dynamically routes complementary scene information to maintain visual consistency. We further introduce DOR-Bench, a benchmark tailored for object removal in dense scenes. Extensive experiments demonstrate that DORS outperforms state-of-the-art methods, particularly in reducing incomplete removal and duplicate artifacts. The code will be available at https://github.com/httang1224/DORS.
发表机构
- School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。
