零样本3D补全新方法，无需训练即可适配多种形状
LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency
- 分两阶段补全：先保留原形貌，再隐式融合新旧区域边界
- 零训练适配不同3D基础模型，跨类别通用性强
- 自建多场景数据集，支持真实与合成数据的全面评估
本文提出LaS-Comp，一种零样本、类别无关的3D形状补全方法，利用3D基础模型丰富的几何先验，实现对多种部分观测的补全。其核心贡献包括：（1）采用双阶段设计，第一阶段显式替换保留原始观测几何结构以保证还原精度；第二阶段隐式优化确保观测与生成区域间无缝衔接；（2）完全无需训练，兼容多种3D基础模型；（3）构建Omni-Comp基准，融合真实世界与合成数据，覆盖多样且具有挑战性的部分观测模式，支持更全面、真实的评估。定量与定性实验表明，该方法显著优于现有最先进方法。代码与数据将公开于https://github.com/DavidYan2001/LaS-Comp。
原文摘要 · Abstract (English)
This paper introduces LaS-Comp, a zero-shot and category-agnostic approach that leverages the rich geometric priors of 3D foundation models to enable 3D shape completion across diverse types of partial observations. Our contributions are threefold: First, \ourname{} harnesses these powerful generative priors for completion through a complementary two-stage design: (i) an explicit replacement stage that preserves the partial observation geometry to ensure faithful completion; and (ii) an implicit refinement stage ensures seamless boundaries between the observed and synthesized regions. Second, our framework is training-free and compatible with different 3D foundation models. Third, we introduce Omni-Comp, a comprehensive benchmark combining real-world and synthetic data with diverse and challenging partial patterns, enabling a more thorough and realistic evaluation. Both quantitative and qualitative experiments demonstrate that our approach outperforms previous state-of-the-art approaches. Our code and data will be available at \href{https://github.com/DavidYan2001/LaS-Comp}{LaS-Comp}.
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。