UnScene3D：面向室内场景的无监督三维实例分割
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
AI总结：
UnScene3D提出首个全无监督室内三维实例分割方法，利用自监督颜色与几何特征生成伪掩码并结合几何过分割与自训练，将平均精度提升超过300%。
摘要：
三维实例分割是理解我们周围世界几何结构的基础。现有的三维场景实例分割方法依赖于昂贵的人工三维标注监督。我们提出UnScene3D，这是首个针对室内扫描的类别无关三维实例分割的全无监督三维学习方法。UnScene3D首先利用自监督的颜色和几何特征生成伪掩码，以发现潜在的目标区域。我们在几何过分割的基础上进行操作，从而能够在高分辨率三维数据上实现高效的表示和学习。随后，通过在其自身预测结果上进行自训练来细化粗略的候选区域。我们的方法相比最先进的无监督三维实例分割方法，平均精度得分提升超过300%，证明了即使在具有挑战性、杂乱的三维场景中也能实现有效的实例分割。
英文摘要：
3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensive, manual 3D annotations. We propose UnScene3D, the first fully unsupervised 3D learning approach for class-agnostic 3D instance segmentation of indoor scans. UnScene3D first generates pseudo masks by leveraging self-supervised color and geometry features to find potential object regions. We operate on a basis of geometric oversegmentation, enabling efficient representation and learning on high-resolution 3D data. The coarse proposals are then refined through self-training our model on its predictions. Our approach improves over state-of-the-art unsupervised 3D instance segmentation methods by more than 300% Average Precision score, demonstrating effective instance segmentation even in challenging, cluttered 3D scenes.
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。
