CDIS：通过2D掩码跟踪和3D-2D投影合并实现跨维度类别无关的3D实例分割
CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging
浏览论文内容
中文总结 AI 辅助
研究针对未知环境中机器人系统的类别无关3D实例分割问题，提出CDIS零样本框架，通过跨帧跟踪2D实例掩码并与3D超点关联，在2D和3D间创建反馈循环，实验证明其比现有方法更准确、一致且高效可扩展。
中文摘要 AI 辅助
类别无关的3D实例分割对于在未知环境中运行的机器人系统至关重要，能让机器人感知未见物体以进行可靠操作和导航。现有方法通常将每帧2D实例掩码投影到3D并合并，这常导致物体身份随时间中断并产生碎片化3D实例。我们引入跨维度类别无关的3D实例分割（CDIS），这是一个零样本框架，它能跨帧显式跟踪2D实例掩码并将其与3D超点关联，在2D和3D间创建反馈循环。这种跨维度推理将时间上稳定的2D轨迹与空间上连贯的3D区域相连，无需任何3D特定训练就能生成全局一致的3D实例标签。在基准数据集上的实验表明，CDIS比现有零样本方法具有更高的准确性和一致性，同时保持高效并可扩展到各种现实世界环境。
英文摘要
Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation. Existing approaches typically project per-frame 2D instance masks into 3D and merge them, which often breaks object identities across time and yields fragmented 3D instances. We introduce Cross-Dimensional Class-Agnostic 3D Instance Segmentation (CDIS), a zero-shot framework that explicitly tracks 2D instance masks across frames and associates them with 3D superpoints, creating a feedback loop between 2D and 3D. This cross-dimensional reasoning links temporally stable 2D tracks with spatially coherent 3D regions, producing globally consistent 3D instance labels without any 3D-specific training. Experiments on benchmark datasets demonstrate that CDIS achieves higher accuracy and consistency than state-of-the-art zero-shot methods, while remaining efficient and scalable to diverse real-world environments.
发表机构
- Interdisciplinary Program in AI, Seoul National University（首尔国立大学人工智能跨学科项目）
机构由 AI 辅助整理，请以论文原文为准。
