用扩散策略实现高效泛化3D扫描，抗噪且适应新物体。
ScanDP: Generalizable 3D Scanning with Diffusion Policy
- 采用扩散策略模仿人类扫描行为，数据效率高。
- 在未见物体上覆盖率达92.3%，路径更短且抗传感器噪声。
- 适合机器人3D建模、工业检测等需泛化能力的场景。
基于学习的3D扫描在高效精准获取目标物体信息方面至关重要。然而，现有强化学习方法通常需要大规模训练数据，且难以泛化到未见物体类别。本文提出一种数据高效的3D扫描框架，利用扩散策略模仿人类扫描策略。为提升鲁棒性与泛化能力，采用占用栅格地图而非直接处理点云，增强对噪声的容忍度并适应多样几何形状。同时引入球面空间表示与路径优化相结合的混合方法，确保路径安全与扫描效率，克服传统模仿学习中冗余或不可预测行为的局限。我们在多种未见过的物体（形状与尺度各异）上进行评估，结果表明本方法在覆盖率达92.3%的同时路径更短，且对传感器噪声保持鲁棒。进一步实验证明其在真实场景中具备可行性与稳定性。
原文摘要 · Abstract (English)
Learning-based 3D Scanning plays a crucial role in enabling efficient and accurate scanning of target objects. However, recent reinforcement learning-based methods often require large-scale training data and still struggle to generalize to unseen object categories.In this work, we propose a data-efficient 3D scanning framework that uses Diffusion Policy to imitate human-like scanning strategies. To enhance robustness and generalization, we adopt the Occupancy Grid Mapping instead of direct point cloud processing, offering improved noise resilience and handling of diverse object geometries. We also introduce a hybrid approach combining a sphere-based space representation with a path optimization procedure that ensures path safety and scanning efficiency. This approach addresses limitations in conventional imitation learning, such as redundant or unpredictable behavior. We evaluate our method on diverse unseen objects in both shape and scale. Ours achieves higher coverage and shorter paths than baselines, while remaining robust to sensor noise. We further confirm practical feasibility and stable operation in real-world execution.
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。