统一图元代理用于结构化形状补全
Unified Primitive Proxies for Structured Shape Completion
将图元（primitive）解码从点云级联中解耦为独立通路，并用可学习查询（primitive proxies）一次性前馈输出几何、语义与内点归属，可直接迁移到点云补全、部件级重建与装配式表面重建流程。
原文依据 we present UniCo, which in a single feed-forward pass predicts a set of primitives with complete geometry, semantics, and inlier membership
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论结构化形状补全将缺失几何恢复为图元而非无结构点云，从而使基于图元的表面重建成为可能。我们没有沿用主流的级联式做法，而是重新思考图元与点之间应当如何交互，并发现用一条专门通路在共享形状特征上做注意力来解码图元更为有效。遵循这一原则，我们提出 UniCo，它在单次前馈过程中预测一组具有完整几何、语义与内点归属的图元。为驱动这一统一表示，我们引入图元代理（primitive proxies），即可学习查询，它们被上下文化以产生可直接用于装配的输出。为保证优化的一致性，我们的训练策略通过在线目标更新将图元与点耦合起来。在合成与真实世界基准上，配合四个独立的装配求解器，UniCo 一致优于近期基线，Chamfer 距离最多降低 50%，法向一致性最多提升 7%。这些结果为从不完整数据中进行结构化三维理解提供了一套颇具吸引力的方案。
英文原文摘要 1161 字符
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.