Search papers, labs, and topics across Lattice.
This paper introduces ScanDP, a data-efficient 3D scanning framework leveraging Diffusion Policy to mimic human-like scanning strategies. The method employs Occupancy Grid Mapping for enhanced robustness and generalization to unseen object categories, and combines a sphere-based space representation with path optimization for safety and efficiency. Experiments demonstrate that ScanDP achieves higher coverage and shorter paths compared to baselines, while also exhibiting robustness to sensor noise and practical feasibility in real-world scenarios.
Forget training on massive datasets: this new diffusion policy learns human-like 3D scanning strategies that generalize to unseen objects while being robust to noise.
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.
