用预训练扩散模型零样本组装3D部件，无需标注数据
Leveraging Pretrained Diffusion Models for Zero-Shot Part Assembly
- 用预训练点云扩散模型当判别器引导部件组装
- 理论证明可转为ICP迭代过程，精度超越监督方法
- 新推离策略解决部件重叠，适合机器人自主装配
3D部件组装旨在理解部件间关系并预测其6-DoF位姿，以构建逼真3D形状，满足机器人自主装配的日益需求。现有方法主要依赖有监督神经网络估计各部件变换，需大量人工标注数据。但数据采集成本高，且真实世界中形状与部件变化巨大，使传统方法难以大规模应用。本文首次提出零样本部件组装方法，利用预训练点云扩散模型作为组装过程中的判别器，引导部件操作形成逼真形状。具体地，理论上证明了使用扩散模型进行零样本组装可转化为迭代最近点（ICP）过程；进而提出新颖的推离策略以解决部件重叠问题，进一步提升方法鲁棒性。通过大量实验与强基线方法对比，验证了所提方法的有效性，甚至超越监督学习方法。代码已公开于 https://github.com/Ruiyuan-Zhang/Zero-Shot-Assembly。
原文摘要 · Abstract (English)
3D part assembly aims to understand part relationships and predict their 6-DoF poses to construct realistic 3D shapes, addressing the growing demand for autonomous assembly, which is crucial for robots. Existing methods mainly estimate the transformation of each part by training neural networks under supervision, which requires a substantial quantity of manually labeled data. However, the high cost of data collection and the immense variability of real-world shapes and parts make traditional methods impractical for large-scale applications. In this paper, we propose first a zero-shot part assembly method that utilizes pre-trained point cloud diffusion models as discriminators in the assembly process, guiding the manipulation of parts to form realistic shapes. Specifically, we theoretically demonstrate that utilizing a diffusion model for zero-shot part assembly can be transformed into an Iterative Closest Point (ICP) process. Then, we propose a novel pushing-away strategy to address the overlap parts, thereby further enhancing the robustness of the method. To verify our work, we conduct extensive experiments and quantitative comparisons to several strong baseline methods, demonstrating the effectiveness of the proposed approach, which even surpasses the supervised learning method. The code has been released on https://github.com/Ruiyuan-Zhang/Zero-Shot-Assembly.
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。