迈向 3D 场景理解基础模型：面向点云的实例感知自监督学习
Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds
用正交偏移分支在自监督预训练中同时学语义与几何，并用偏移分布正则与空间聚类正则把实例感知注入点云表征，可直接迁移到点云实例分割/全景分割的预训练阶段，减少对全量微调的依赖。
原文依据 PointINS employs an orthogonal offset branch to jointly learn high-level semantic understanding and geometric reasoning, yielding instance awareness.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期点云自监督学习的进展在无人工标注的情况下显著提升了 3D 场景理解能力。现有方法通过强制增强视图间的特征一致性或掩码场景建模来强调语义感知。然而，所得表征向实例定位的迁移效果较差，且往往需要全量微调才能取得强性能。实例感知是 3D 感知的基本组成部分，因此弥合这一差距对于迈向支持 3D 数据上所有下游任务的真正 3D 基础模型至关重要。在本工作中，我们提出 PointINS，一个面向实例的自监督框架，通过几何感知学习来丰富点云表征。PointINS 采用正交偏移分支，联合学习高层语义理解与几何推理，从而获得实例感知能力。我们识别出对鲁棒实例定位至关重要的两个一致性性质，并将其形式化为互补的正则化策略：偏移分布正则化（ODR），使预测偏移与经验观测到的几何先验对齐；以及空间聚类正则化（SCR），通过伪实例掩码对偏移进行正则化以强制局部一致性。在五个数据集上的大量实验表明，PointINS 在室内实例分割上平均取得 +3.5% 的平均精度均值提升，在室外全景分割上取得 +4.1% 的 PQ 增益，为可扩展的 3D 基础模型铺平了道路。
英文原文摘要 1546 字符
Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across augmented views or by masked scene modeling. However, the resulting representations transfer poorly to instance localization, and often require full finetuning for strong performance. Instance awareness is a fundamental component of 3D perception, thus bridging this gap is crucial for progressing toward true 3D foundation models that support all downstream tasks on 3D data. In this work, we introduce PointINS, an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.PointINS employs an orthogonal offset branch to jointly learn high-level semantic understanding and geometric reasoning, yielding instance awareness. We identify two consistent properties essential for robust instance localization and formulate them as complementary regularization strategies, Offset Distribution Regularization (ODR), which aligns predicted offsets with empirically observed geometric priors, and Spatial Clustering Regularization (SCR), which enforces local coherence by regularizing offsets with pseudo-instance masks. Through extensive experiments across five datasets, PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation, paving the way for scalable 3D foundation models.