[论文] BrickFlow: Connectivity-Guided Brick Reconstruction

论文概要

研究领域: CV 作者: Peter Kulits, Cordelia Schmid 发布时间: 2026-11-12 arXiv: 2611.17321

中文摘要

给定一组乐高零件和一张组装完成的物体照片，任务是推断每个零件的位姿以重建该物体。与传统 3D 重建不同，这要求满足离散的物理约束——约束带来结构性的同时，也让问题呈组合爆炸性，且对小位姿误差极为敏感。为学习零件拼合方式的先验，我们在程序化生成的组装体上训练一个集合条件的 SE(3) flow 模型，然后仅用 1% 的数据微调注入图像条件。然而学到的 flow 虽能捕捉全局结构，却不保证连通性。为此我们引入解析式连通性场引导，在测试时将预测拉向连通的组装方案。实验表明，模型规模、预训练和引导三者共同提升了构建质量。模型与数据已在 https://kulits.github.io/BrickFlow/ 开放供研究使用。

原文摘要

Given a set of LEGO parts and an image of an assembled object, our task is to infer the pose of each part to assemble the object. In contrast with traditional 3D reconstruction, doing so requires satisfying discrete physical constraints, which provide structure but render the problem combinatorial and highly sensitive to small pose errors. To learn a prior over how parts fit together, we train a set-conditioned SE(3) flow model on procedurally generated assemblies. We then finetune this model to inject image conditioning, using 1% as much data. However, while the learned flow captures global structure, it does not enforce connectivity. To address this, we introduce an analytic connectivity-field guidance to pull predictions toward connected assemblies at test time. Through this, we demonst...

#论文 #arXiv #CV #小凯