Clutt3R-Seg：用于语言引导抓取的稀疏视角3D实例分割
Clutt3R-Seg: Sparse-view 3D Instance Segmentation for Language-grounded Grasping in Cluttered Scenes
AI总结：
Clutt3R-Seg通过引入层次实例树和开放词汇语义嵌入，实现了在杂乱场景中语言引导抓取的高效3D实例分割。
摘要：
可靠的3D实例分割是语言引导机器人操作的基础。其关键应用在于杂乱环境，其中遮挡、有限视角和噪声掩码会降低感知能力。为了解决这些挑战，我们提出了Clutt3R-Seg，一种零样本管道，用于在杂乱场景中进行语言引导抓取的稳健3D实例分割。我们的核心思想是引入语义提示的层次实例树。不同于先前方法试图细化噪声掩码，我们的方法利用它们作为信息提示：通过跨视角分组和条件替换，树抑制了过分割和欠分割，产生视图一致的掩码和稳健的3D实例。每个实例都增强了开放词汇语义嵌入，使能够从自然语言指令中准确选择目标。为了处理多阶段任务中的场景变化，我们进一步引入了一种一致性感知更新，保留了仅从单一交互后图像中保留的实例对应关系，允许高效适应而无需重新扫描。Clutt3R-Seg在合成和真实世界数据集上进行了评估，并在真实机器人上进行了验证。在所有设置中，它在杂乱和稀疏视角场景中都优于最先进的基线。即使在最具有挑战性的高杂乱序列中，Clutt3R-Seg也实现了61.66的AP@25，比基线高出2.2倍，并且仅使用四个输入视角就超过了使用八个视角的MaskClustering。代码可在：https://github.com/jeonghonoh/clutt3r-seg获得。
英文摘要：
Reliable 3D instance segmentation is fundamental to language-grounded robotic manipulation. Its critical application lies in cluttered environments, where occlusions, limited viewpoints, and noisy masks degrade perception. To address these challenges, we present Clutt3R-Seg, a zero-shot pipeline for robust 3D instance segmentation for language-grounded grasping in cluttered scenes. Our key idea is to introduce a hierarchical instance tree of semantic cues. Unlike prior approaches that attempt to refine noisy masks, our method leverages them as informative cues: through cross-view grouping and conditional substitution, the tree suppresses over- and under-segmentation, yielding view-consistent masks and robust 3D instances. Each instance is enriched with open-vocabulary semantic embeddings, enabling accurate target selection from natural language instructions. To handle scene changes during multi-stage tasks, we further introduce a consistency-aware update that preserves instance correspondences from only a single post-interaction image, allowing efficient adaptation without rescanning. Clutt3R-Seg is evaluated on both synthetic and real-world datasets, and validated on a real robot. Across all settings, it consistently outperforms state-of-the-art baselines in cluttered and sparse-view scenarios. Even on the most challenging heavy-clutter sequences, Clutt3R-Seg achieves an AP@25 of 61.66, over 2.2x higher than baselines, and with only four input views it surpasses MaskClustering with eight views by more than 2x. The code is available at: https://github.com/jeonghonoh/clutt3r-seg.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
