提出可调控粒度的3D点云部件分割方法，解决视图不一致问题。
S2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds
- 用2D先验+3D对比学习，生成全局一致的点特征
- 通过连续尺度信号实现实时分割粒度调整
- 构建超10万样本数据集，支持复杂结构分割
部件级点云分割在3D计算机视觉中受到广泛关注。然而，现有方法面临两大挑战：原生3D模型因数据稀缺导致泛化能力差，引入2D预训练知识又常引发不同视角间分割结果不一致。为此，本文提出S2AM3D，将2D分割先验与3D一致性监督结合。设计点一致部件编码器，通过原生3D对比学习聚合多视角2D特征，生成全局一致的点特征。进一步提出尺度感知提示解码器，通过连续尺度信号实现实时调节分割粒度。同时，构建大规模高质量部件级点云数据集，包含超过10万样本，为模型训练提供充足监督信号。大量实验表明，S2AM3D在多种评估设置下均达到领先性能，对复杂结构及尺寸差异显著的部件展现出优异鲁棒性与可控性。
原文摘要 · Abstract (English)
Part-level point cloud segmentation has recently attracted significant attention in 3D computer vision. Nevertheless, existing research is constrained by two major challenges: native 3D models lack generalization due to data scarcity, while introducing 2D pre-trained knowledge often leads to inconsistent segmentation results across different views. To address these challenges, we propose S2AM3D, which incorporates 2D segmentation priors with 3D consistent supervision. We design a point-consistent part encoder that aggregates multi-view 2D features through native 3D contrastive learning, producing globally consistent point features. A scale-aware prompt decoder is then proposed to enable real-time adjustment of segmentation granularity via continuous scale signals. Simultaneously, we introduce a large-scale, high-quality part-level point cloud dataset with more than 100k samples, providing ample supervision signals for model training. Extensive experiments demonstrate that S2AM3D achieves leading performance across multiple evaluation settings, exhibiting exceptional robustness and controllability when handling complex structures and parts with significant size variations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。