用统一代理机制一次性完成3D形状的结构化补全。
Unified Primitive Proxies for Structured Shape Completion
- 设计可学习的原始代理，专注生成带几何、语义和归属信息的完整原始体。
- 在合成与真实数据上，相比基线降低50%的Chamfer距离，法向一致性提升7%。
- 适合需要精确3D重建的工业设计、机器人抓取等场景。
结构化形状补全旨在以基本几何体而非无序点云恢复缺失几何，支持基于原始体的表面重建。不同于现有级联方法，本文重新思考原始体与点云的交互方式，提出在专用路径中解码原始体，并关注共享形状特征。基于此，提出UniCo，在一次前馈过程中预测一组具备完整几何、语义及内点归属关系的原始体。为实现统一表征，引入可学习的原始代理（primitive proxies），通过上下文感知生成可装配输出。训练策略采用在线目标更新，确保原始体与点云协同优化。在包含四个独立装配求解器的合成与真实世界基准上，UniCo持续优于近期基线，Chamfer距离最高降低50%，法向一致性最高提升7%。结果表明该方法为不完整数据下的结构化3D理解提供了高效方案。项目页：https://unico-completion.github.io。
原文摘要 · Abstract (English)
Structured shape completion recovers missing geometry as primitives rather than as unstructured points, which enables primitive-based surface reconstruction. Instead of following the prevailing cascade, we rethink how primitives and points should interact, and find it more effective to decode primitives in a dedicated pathway that attends to shared shape features. Following this principle, we present UniCo, which in a single feed-forward pass predicts a set of primitives with complete geometry, semantics, and inlier membership. To drive this unified representation, we introduce primitive proxies, learnable queries that are contextualized to produce assembly-ready outputs. To ensure consistent optimization, our training strategy couples primitives and points with online target updates. Across synthetic and real-world benchmarks with four independent assembly solvers, UniCo consistently outperforms recent baselines, lowering Chamfer distance by up to 50% and improving normal consistency by up to 7%. These results establish an attractive recipe for structured 3D understanding from incomplete data. Project page: https://unico-completion.github.io.
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。