无需场景监督，让3D物体表示自动适应真实场景
EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
- 动态优化物体候选，持续适配真实数据分布
- 重建部分几何结构，提升遮挡下分割精度
- 适合无标注真实3D场景的实例分割任务
我们提出 EvObj，一种无需场景监督的3D实例分割方法，用于弥合合成预训练数据与真实点云之间的几何域差异。现有方法在将合成数据（如 ShapeNet）中的物体先验迁移至真实扫描（如 ScanNet）时，常因形态差异和遮挡伪影导致结构不匹配。EvObj 引入两个创新模块：(1) 物体判别模块，动态优化物体候选，实现物体先验对目标域的持续自适应；(2) 物体补全模块，在发现物体后重建部分几何结构。我们在真实与合成数据集上进行了大量实验，结果表明其性能全面优于现有基线，达到当前最优水平。
原文摘要 · Abstract (English)
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.
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。