EvObj：无需场景监督学习演化式以对象为中心表征的 3D 实例分割
EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
把「对象先验从合成数据迁移到真实扫描」拆成可迭代的对象判别（动态精炼候选）与对象补全（重建遮挡几何）两个模块，为无监督 3D 实例分割提供了一条不依赖场景级标注、可跨域自适应的路线，可直接用于点云实例分割的预训练-微调流程。
原文依据 An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 EvObj，用于无监督 3D 实例分割，旨在弥合合成预训练数据与真实世界点云之间的几何域差距。现有方法在将对象先验从合成数据集（如 ShapeNet）迁移到真实扫描（如 ScanNet）时，会因形态变化与遮挡伪影而出现结构不一致的问题。为解决该问题，EvObj 集成了两个创新模块：(1) 对象判别模块，动态精炼对象候选，使对象先验能够持续适应目标域；(2) 对象补全模块，在发现对象后重建其不完整的几何。我们在真实世界与合成数据集上开展了大量实验，结果表明其 3D 对象分割性能优于所有基线，并取得了最优结果。
英文原文摘要 885 字符
We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when transferring object priors from synthetic datasets (e.g., ShapeNet) to real scans (e.g., ScanNet), particularly due to morphological variations and occlusion artifacts. To address this, EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.