ScanDP: Generalizable 3D Scanning with Diffusion Policy

TL;DR

ScanDP introduces a data-efficient, generalizable 3D scanning framework that mimics human strategies using diffusion policies, improving robustness, coverage, and efficiency across diverse unseen objects.

Contribution

The paper proposes a novel diffusion policy-based framework with occupancy grid mapping and hybrid space representation for improved 3D scanning generalization and efficiency.

Findings

Achieves higher coverage than baseline methods.

Uses shorter paths for scanning.

Remains robust to sensor noise and real-world conditions.

Abstract

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.