BEEP3D：面向3D实例分割的框监督端到端伪掩码生成
BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
AI总结：
BEEP3D提出框监督的端到端3D实例分割方法，采用学生-教师框架和两种一致性损失，在ScanNetV2和S3DIS上达到先进性能。
摘要：
3D实例分割对于理解复杂的3D环境至关重要，然而全监督方法需要密集的点级标注，导致高昂的标注成本和人力开销。为缓解这一问题，框级标注作为一种更弱但更具可扩展性的监督形式被探索。然而，框标注在重叠区域固有地引入歧义，使得精确的点到实例分配具有挑战性。近期方法通过训练专用伪标签器在额外训练阶段生成伪掩码来解决这种歧义。然而，此类两阶段流程往往增加整体训练时间和复杂度，并阻碍端到端优化。为克服这些挑战，我们提出BEEP3D——用于3D实例分割的框监督端到端伪掩码生成。BEEP3D采用学生-教师框架，其中教师模型充当伪标签器，并通过指数移动平均由学生模型更新。为了更好地引导教师模型生成精确的伪掩码，我们引入基于实例中心的查询细化，增强位置查询定位并利用实例中心附近的特征。此外，我们设计了两种新颖的损失——查询一致性损失和掩码特征一致性损失——以对齐预测与伪掩码之间的语义和几何信号。在ScanNetV2和S3DIS数据集上的大量实验表明，BEEP3D在保持计算效率的同时，与最先进的弱监督方法相比取得了具有竞争力或更优的性能。
英文摘要：
3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor overhead. To mitigate this, box-level annotations have been explored as a weaker but more scalable form of supervision. However, box annotations inherently introduce ambiguity in overlapping regions, making accurate point-to-instance assignment challenging. Recent methods address this ambiguity by generating pseudo-masks through training a dedicated pseudo-labeler in an additional training stage. However, such two-stage pipelines often increase overall training time and complexity, hinder end-to-end optimization. To overcome these challenges, we propose BEEP3D-Box-supervised End-to-End Pseudo-mask generation for 3D instance segmentation. BEEP3D adopts a student-teacher framework, where the teacher model serves as a pseudo-labeler and is updated by the student model via an Exponential Moving Average. To better guide the teacher model to generate precise pseudo-masks, we introduce an instance center-based query refinement that enhances position query localization and leverages features near instance centers. Additionally, we design two novel losses-query consistency loss and masked feature consistency loss-to align semantic and geometric signals between predictions and pseudo-masks. Extensive experiments on ScanNetV2 and S3DIS datasets demonstrate that BEEP3D achieves competitive or superior performance compared to state-of-the-art weakly supervised methods while remaining computationally efficient.
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。
