V^2-SAM：将 SAM2 与多提示词专家结合用于跨视角目标对应
V^2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
把 SAM2 从单视角分割迁移到跨视角对应，关键手段是两类提示生成器：基于 DINOv3 特征的坐标式锚框提示（首次让 SAM2 支持跨视角坐标提示）与特征/结构双重对齐的视觉提示匹配器，并用循环一致性做专家选择，可直接复用到 ego-exo 分割、跨视角跟踪等需要把基础分割模型扩展到多视角设定的场景。
原文依据 unlocks coordinate-based prompting for SAM2 in cross-view scenarios
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论跨视角目标对应以自我中心-外中心（ego-exo）目标对应这一代表性任务为例，旨在为不同视角（如自我中心视角与外中心视角）下的同一目标建立一致的关联。由于视角与外观的剧烈变化，该任务面临显著挑战，使得现有分割模型（如 SAM2）难以直接应用。为此，我们提出 V^2-SAM，一个统一的跨视角目标对应框架，通过两个互补的提示词生成器将 SAM2 从单视角分割适配到跨视角对应。具体而言，跨视角锚框提示词生成器（V^2-Anchor）构建于 DINOv3 特征之上，建立具有几何感知的对应关系，并首次在跨视角场景中为 SAM2 解锁基于坐标的提示方式；而跨视角视觉提示词生成器（V^2-Visual）通过一种新颖的视觉提示词匹配器，从特征与结构两个角度对齐自我中心与外中心的表征，从而增强外观引导的线索。为有效发挥两类提示词各自的优势，我们进一步采用多专家设计，并引入事后循环一致性选择器（PCCS），基于循环一致性自适应地选择最可靠的专家。大量实验验证了 V^2-SAM 的有效性，在 Ego-Exo4D（自我中心-外中心目标对应）、DAVIS-2017（视频目标跟踪）与 HANDAL-X（面向机器人的跨视角对应）上取得了新的最优性能。
英文原文摘要 1536 字符
Cross-view object correspondence, exemplified by the representative task of ego-exo object correspondence, aims to establish consistent associations of the same object across different viewpoints (e.g., ego-centric and exo-centric). This task poses significant challenges due to drastic viewpoint and appearance variations, making existing segmentation models, such as SAM2, non-trivial to apply directly. To address this, we present V^ 2 -SAM, a unified cross-view object correspondence framework that adapts SAM2 from single-view segmentation to cross-view correspondence through two complementary prompt generators. Specifically, the Cross-View Anchor Prompt Generator (V^ 2 -Anchor), built upon DINOv3 features, establishes geometry-aware correspondences and, for the first time, unlocks coordinate-based prompting for SAM2 in cross-view scenarios, while the Cross-View Visual Prompt Generator (V^ 2 -Visual) enhances appearance-guided cues via a novel visual prompt matcher that aligns ego-exo representations from both feature and structural perspectives. To effectively exploit the strengths of both prompts, we further adopt a multi-expert design and introduce a Post-hoc Cyclic Consistency Selector (PCCS) that adaptively selects the most reliable expert based on cyclic consistency. Extensive experiments validate the effectiveness of V^ 2 -SAM, achieving new state-of-the-art performance on Ego-Exo4D (Ego-Exo object correspondence), DAVIS-2017 (video object tracking), and HANDAL-X (robotic-ready cross-view correspondence).